© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1511
    Prev
    Next
    INDEX
    Explanations

    mentions of involuntary body reactions presumably in reaction to some outside stimuli

    oai_token-act-pair · gemini-2.0-flash

    Body parts

    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
     للمعارف
    -0.55
    Diweddarwch
    -0.52
    expandindo
    -0.51
    classmethod
    -0.50
    TestingModule
    -0.47
     varargin
    -0.47
    RenderAtEndOf
    -0.45
     nahilalakip
    -0.44
     препратки
    -0.44
     }}</
    -0.43
    POSITIVE LOGITS
     t
    0.67
    ANTLR
    0.66
    VIAF
    0.64
    Παραπομπές
    0.59
    Jegyzetek
    0.57
    Erstellt
    0.56
    getStatusCode
    0.49
    ToScroll
    0.49
     refreshToken
    0.49
    nobyl
    0.49
    Activations Density 5.392%

    No Known Activations