© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10301
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific game or fictional world, potentially involving character names, items, or locations.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     
    -0.63
     I
    -0.63
    <eos>
    -0.59
     Re
    -0.59
     [
    -0.56
     .
    -0.56
     M
    -0.56
     *
    -0.56
     In
    -0.56
     (
    -0.54
    POSITIVE LOGITS
     ―――――
    1.14
     CreateTagHelper
    1.13
     myſelf
    1.09
     Theſe
    1.08
     Efq
    1.05
     itſelf
    1.02
    expandindo
    0.96
     Monfieur
    0.95
     Jefus
    0.94
     iſt
    0.93
    Activations Density 0.735%

    No Known Activations