© 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. 6527
    Prev
    Next
    INDEX
    Explanations

    a mix of negative language, work culture buzzwords, scientific abbreviations, and DNA research terms.

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific 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
     ups
    -1.11
     Ks
    -1.08
    ms
    -1.08
    ens
    -1.05
    gs
    -1.05
    Ns
    -1.02
    Ks
    -1.02
    ns
    -1.02
    ans
    -1.01
     Ups
    -1.01
    POSITIVE LOGITS
     <=",
    0.56
     ComVisible
    0.48
     månader
    0.46
     religieuses
    0.45
    govina
    0.45
    CJK
    0.45
     timmar
    0.45
     autorytatywna
    0.42
     scolaires
    0.42
    Matrices
    0.42
    Activations Density 2.912%

    No Known Activations