© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4098
    Prev
    Next
    INDEX
    Explanations

    discourse markers, but is particularly fond of semicolons

    oai_token-act-pair · gemini-2.0-flash

    ;

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     hence
    -0.88
    hence
    -0.84
    CppCodeGen
    -0.81
    however
    -0.79
     therefore
    -0.79
     thus
    -0.78
     moreover
    -0.77
     however
    -0.75
     furthermore
    -0.74
     pinulongan
    -0.74
    POSITIVE LOGITS
    '
    0.64
    ~
    0.58
    -*
    0.54
    *
    0.53
    \)
    0.52
    []);
    0.51
    --
    0.50
    *[
    0.50
    ’
    0.50
    »-
    0.49
    Activations Density 6.899%

    No Known Activations