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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14318
    Prev
    Next
    INDEX
    Explanations

    adverbs and words describing lab procedures

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     يتيمه
    -0.73
    Personensuche
    -0.67
    PathVariable
    -0.63
     للمعارف
    -0.59
    enterOuterAlt
    -0.58
     Grecian
    -0.56
     freestanding
    -0.56
    Geplaatst
    -0.56
    ocere
    -0.55
    standing
    -0.54
    POSITIVE LOGITS
     zostały
    0.59
    osamente
    0.53
    انتهای
    0.53
    ياه
    0.52
    都被
    0.52
     kuitenkin
    0.51
    \"");
    0.51
    被他
    0.50
     clip
    0.50
     dignité
    0.50
    Activations Density 2.679%

    No Known Activations