© 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. 3878
    Prev
    Next
    INDEX
    Explanations

    a mix of tokens related to language, geography, and potentially some code

    oai_token-act-pair · gemini-2.0-flash

    "us"

    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
     TU
    -0.76
     MU
    -0.72
    u
    -0.69
     WU
    -0.68
     LU
    -0.68
    TU
    -0.67
    脚注の使い方
    -0.67
     IU
    -0.64
    MU
    -0.63
     NU
    -0.63
    POSITIVE LOGITS
     us
    1.21
    us
    1.20
    US
    1.07
     Us
    1.01
     US
    0.96
    Us
    0.91
    usar
    0.79
    usan
    0.71
    OGND
    0.67
    usk
    0.66
    Activations Density 1.113%

    No Known Activations