© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    the names of variables or methods in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    say parenthesis and code symbols

    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
    contentLoaded
    -0.65
    DockStyle
    -0.63
    ,
    -0.60
     initComponents
    -0.60
    StructEnd
    -0.60
    :',
    -0.59
    :",
    -0.58
    {}",
    -0.58
    :
    -0.57
    ':
    -0.57
    POSITIVE LOGITS
     Efq
    0.80
     ſmall
    0.68
     houſe
    0.65
     pleaſure
    0.65
     purpoſe
    0.61
     Theſe
    0.60
     raiſ
    0.60
     ſtate
    0.60
     Anſ
    0.60
    ſelf
    0.60
    Activations Density 11.218%

    No Known Activations