© 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. 14631
    Prev
    Next
    INDEX
    Explanations

    capitalized fragments of words and abbreviations, especially initials embedded in longer words

    oai_token-act-pair · gemini-2.0-flash

    proper nouns or names

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

    courtroom testimony

    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
    webElementXpaths
    -0.65
    Referències
    -0.61
    awtextra
    -0.48
    Izvori
    -0.47
    CppCodeGen
    -0.46
     Birth
    -0.46
     समीक्षक
    -0.45
    gaz
    -0.45
    oredCriteria
    -0.45
    Provision
    -0.44
    POSITIVE LOGITS
    Tembelea
    0.67
    曖昧さ回避
    0.63
     كومونز
    0.58
     الحره
    0.57
     înc
    0.56
    Addo
    0.55
     normaux
    0.55
    UpInside
    0.55
     незавершена
    0.55
    Comentários
    0.55
    Activations Density 0.113%

    No Known Activations