© 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. 6180
    Prev
    Next
    INDEX
    Explanations

    mathematical and date symbols with additional hits on content about Poland

    oai_token-act-pair · gemini-2.0-flash

    say "d" words

    np_max-act-logits · gemini-2.0-flash

    punctuation Method used: 1 — because max-activating tokens are punctuation — punctuation

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ⓧ
    -0.69
     <=",
    -0.67
    findpost
    -0.67
     виправивши
    -0.66
     unknownFields
    -0.65
     useDispatch
    -0.62
    AddHtmlAttribute
    -0.60
    UnsafeEnabled
    -0.60
    TypedDataSet
    -0.57
     ostavi
    -0.57
    POSITIVE LOGITS
    de
    1.18
    da
    1.09
    d
    1.01
    des
    1.00
    der
    0.99
    das
    0.94
    di
    0.85
    ds
    0.85
    del
    0.83
    dah
    0.83
    Activations Density 18.883%

    No Known Activations