© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13174
    Prev
    Next
    INDEX
    Explanations

    database related code excerpts

    oai_token-act-pair · gemini-2.0-flash

    SQL code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AndFlush
    -0.48
    CreateModel
    -0.47
    AutoScaleMode
    -0.44
    dy
    -0.43
    WriteByte
    -0.43
    ud
    -0.41
     comprennent
    -0.41
     stands
    -0.41
    thaw
    -0.40
    ça
    -0.40
    POSITIVE LOGITS
     estekak
    0.87
     intptr
    0.82
    GraphicsUnit
    0.79
     صوتيه
    0.77
     كومونز
    0.75
    
    0.74
    Xna
    0.74
    脚注の使い方
    0.74
     esternos
    0.71
    исленность
    0.68
    Activations Density 0.317%

    No Known Activations