© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5235
    Prev
    Next
    INDEX
    Explanations

    quotes, specifically the words and punctuation that come before and after the quoted speech

    oai_token-act-pair · gemini-2.0-flash

    quoted speech

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     مشين
    -0.67
    RenderAtEndOf
    -0.65
    umon
    -0.57
     stanovnika
    -0.57
     AssemblyVersion
    -0.57
    InputBorder
    -0.57
     initComponents
    -0.52
    migrationBuilder
    -0.52
    AutoScaleMode
    -0.50
    mbg
    -0.50
    POSITIVE LOGITS
     helyez
    0.50
     said
    0.50
     interessa
    0.48
    sprung
    0.48
     affirmé
    0.47
    assumed
    0.46
     zau
    0.46
     confessed
    0.46
     métiers
    0.46
     menyebut
    0.45
    Activations Density 1.411%

    No Known Activations