© 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. 6144
    Prev
    Next
    INDEX
    Explanations

    words related to fictional universes, including character or group names, place names, and objects.

    oai_token-act-pair · 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
    liceerd
    -0.67
    AddTagHelper
    -0.62
    SCO
    -0.60
    UserScript
    -0.60
    [::-
    -0.60
    zbęd
    -0.59
    elemField
    -0.58
    rogly
    -0.57
     विश्वसनीयता
    -0.57
     Reſ
    -0.57
    POSITIVE LOGITS
     kiin
    0.59
     religieuses
    0.58
     brancas
    0.57
     pinggang
    0.55
     ulteriori
    0.53
     sekal
    0.52
     leher
    0.52
     typelib
    0.51
     faibles
    0.51
     similar
    0.51
    Activations Density 24.495%

    No Known Activations