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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 8586
    Prev
    Next
    INDEX
    Explanations

    lines of code consisting only of whitespace and curly braces

    oai_token-act-pair · gemini-2.0-flash

    code and config files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ↵
    -0.27
    ...
    -0.25
    <b>
    -0.23
    .
    -0.23
    "
    -0.23
    
    -0.21
    、
    -0.20
    ,
    -0.20
    /
    -0.20
    “
    -0.19
    POSITIVE LOGITS
     myſelf
    1.23
    ^(@)
    1.13
     ainfi
    1.09
    ſelf
    1.07
     itſelf
    1.05
     Monfieur
    1.05
     autorytatywna
    1.04
     purpoſe
    1.02
    ſelves
    1.02
     himſelf
    1.02
    Activations Density 9.782%

    No Known Activations