© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9374
    Prev
    Next
    INDEX
    Explanations

    a wide variety of seemingly unrelated words that are often parts of speech other than nouns or verbs and that appear in a variety of contexts

    oai_token-act-pair · gemini-2.0-flash

    financial and administrative terms

    np_token-act-pair-logits · gpt-4o-mini

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Référence
    -0.66
    RefNanny
    -0.56
    jaja
    -0.53
     ment
    -0.52
    Fone
    -0.52
    JpaRepository
    -0.51
    IPAC
    -0.51
    Източници
    -0.51
     BorderRadius
    -0.50
     pare
    -0.50
    POSITIVE LOGITS
     vux
    0.63
     nahilalakip
    0.58
     dépenses
    0.56
     étrangères
    0.56
     citoy
    0.56
     numéros
    0.54
     quæ
    0.54
     frais
    0.53
     commandés
    0.53
     démocr
    0.52
    Activations Density 0.879%

    No Known Activations