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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16291
    Prev
    Next
    INDEX
    Explanations

    pronouns and adjectives

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     fact
    -0.87
     uncertainty
    -0.82
    omeness
    -0.81
     suspicion
    -0.80
     influence
    -0.80
     ambiguity
    -0.80
     experience
    -0.79
     debate
    -0.78
     variation
    -0.77
     criticism
    -0.77
    POSITIVE LOGITS
     prochaine
    0.46
     verke
    0.44
     connais
    0.44
    ArrowToggle
    0.42
    ódz
    0.42
    parian
    0.41
     caméra
    0.41
    Datuak
    0.41
    GeoNames
    0.40
    estinian
    0.40
    Activations Density 12.967%

    No Known Activations