© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11694
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially people's names

    oai_token-act-pair · gemini-2.0-flash

    People's names/biographies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     المعيارى
    -0.88
    ValueStyle
    -0.83
     disambiguazione
    -0.77
     ISNI
    -0.75
    SourceChecksum
    -0.73
    AndEndTag
    -0.69
     صوتيه
    -0.69
    Rohy
    -0.68
     autorytatywna
    -0.68
    енча
    -0.67
    POSITIVE LOGITS
    AddHtmlAttribute
    0.55
     akik
    0.45
     مشين
    0.44
    exactly
    0.42
     endwhile
    0.42
    ğından
    0.42
    endsection
    0.42
     The
    0.41
     she
    0.40
    ことから
    0.40
    Activations Density 4.037%

    No Known Activations