© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9236
    Prev
    Next
    INDEX
    Explanations

    words in a foreign language related to agreements or terms of service

    oai_token-act-pair · gemini-2.0-flash

    account verification terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     p
    -0.44
    {{
    -0.43
    王国
    -0.41
    бле
    -0.41
     so
    -0.40
    ure
    -0.40
     Sab
    -0.38
    bbene
    -0.38
    mtd
    -0.38
     P
    -0.38
    POSITIVE LOGITS
     itſelf
    0.87
     Efq
    0.83
    enderror
    0.79
    ')")
    0.78
     leaſt
    0.77
    ')));
    0.77
     }}$}
    0.77
    InlineData
    0.77
     gynhyrchwyd
    0.75
    +#+#
    0.74
    Activations Density 15.850%

    No Known Activations