© 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. 14918
    Prev
    Next
    INDEX
    Explanations

    words and phrases from different languages in English text

    oai_token-act-pair · gemini-2.0-flash

    programming or technical terms

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

    code snippets

    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
     Cæsar
    -0.56
    AttributeSet
    -0.52
     disambiguazione
    -0.49
    Reparto
    -0.47
    etje
    -0.47
     Rites
    -0.47
    вро
    -0.47
    ExtendWith
    -0.46
    ocarditis
    -0.46
    isms
    -0.46
    POSITIVE LOGITS
    WEBPACK
    0.63
    %;">
    0.60
    nolia
    0.60
     intptr
    0.56
    cipar
    0.56
     supplé
    0.54
     ProtoMessage
    0.54
    Controllo
    0.53
    ună
    0.52
    DNEY
    0.52
    Activations Density 0.474%

    No Known Activations