© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14464
    Prev
    Next
    INDEX
    Explanations

    mathematical phrases

    oai_token-act-pair · gemini-2.0-flash

    stage performance or questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    údio
    -0.44
     itinéraires
    -0.38
     dual
    -0.37
    łog
    -0.37
    mayr
    -0.37
     مشاور
    -0.36
     bit
    -0.36
    lí
    -0.36
    imb
    -0.36
     //
    -0.35
    POSITIVE LOGITS
    WriteBarrier
    0.99
    ValueStyle
    0.94
    ValueGeneration
    0.85
    afficheront
    0.83
     Efq
    0.83
     wireType
    0.82
     nahilalakip
    0.81
     itſelf
    0.81
    StructEnd
    0.77
     Jefus
    0.77
    Activations Density 2.702%

    No Known Activations