© 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. 599
    Prev
    Next
    INDEX
    Explanations

    instances of the strings "kam" and "ham" and related words like "gamification"

    oai_token-act-pair · 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
    awtextra
    -0.72
    χη
    -0.72
    ResumeLayout
    -0.72
     TextInputType
    -0.71
    TestingModule
    -0.69
    Autoritní
    -0.69
     BrowserModule
    -0.68
    KommentareTeilen
    -0.68
    httphttps
    -0.68
    KEYCODE
    -0.67
    POSITIVE LOGITS
    ce
    0.31
    образие
    0.31
    nă
    0.30
    "});
    0.29
     constructor
    0.29
    🥃
    0.28
    Object
    0.28
    uda
    0.28
    usahaan
    0.28
    addParameter
    0.28
    Activations Density 1.019%

    No Known Activations