© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are technical and specific to a topic

    oai_token-act-pair · gemini-2.0-flash

    Formal/scientific/legal/medical texts

    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
    s
    -0.91
    sar
    -0.81
    sor
    -0.77
    sf
    -0.75
    san
    -0.75
    sr
    -0.75
    sn
    -0.73
    sat
    -0.72
    sj
    -0.68
    sam
    -0.68
    POSITIVE LOGITS
    izing
    0.55
    netics
    0.53
    ism
    0.52
    istas
    0.52
    beek
    0.51
    ized
    0.51
    iewicz
    0.51
    bahn
    0.50
    minds
    0.50
    ophobia
    0.50
    Activations Density 13.050%

    No Known Activations