© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12425
    Prev
    Next
    INDEX
    Explanations

    references to tables

    oai_token-act-pair · gemini-2.0-flash

    references to tables and data representations

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

    Table

    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
    ConstraintMaker
    -0.78
    PyExc
    -0.73
    zzleHttp
    -0.73
     nahilalakip
    -0.73
    writeFieldEnd
    -0.71
    GraphicsUnit
    -0.70
    脚注の使い方
    -0.68
     surla
    -0.66
     doInBackground
    -0.66
     pinulongan
    -0.61
    POSITIVE LOGITS
     
    0.48
     "..\..\
    0.47
    detectChanges
    0.44
    htbp
    0.43
     on
    0.43
    '.$
    0.43
     t
    0.42
     '
    0.42
     "..\..\..\
    0.42
     one
    0.42
    Activations Density 3.140%

    No Known Activations