© 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. 8033
    Prev
    Next
    INDEX
    Explanations

    short words and punctuation

    oai_token-act-pair · gemini-2.0-flash

    '

    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
    ốm
    -0.49
    HostException
    -0.47
    loaders
    -0.44
    Dane
    -0.43
     виправивши
    -0.42
    ORS
    -0.41
    ữu
    -0.41
    たまた
    -0.41
    igraph
    -0.41
    setSubject
    -0.40
    POSITIVE LOGITS
    er
    0.67
    @[+][
    0.64
    Bronnen
    0.63
    expandindo
    0.61
    ⓧ
    0.60
    inyin
    0.57
    хьтан
    0.57
    guang
    0.56
    orghini
    0.55
    Zhang
    0.54
    Activations Density 18.418%

    No Known Activations