© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8082
    Prev
    Next
    INDEX
    Explanations

    scientific writing where numbered sections can be clearly identified including titles and references to studies and experiments

    oai_token-act-pair · gemini-2.0-flash

    archaic or literary terms

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     via
    -0.60
     dis
    -0.58
     per
    -0.57
     in
    -0.57
     sin
    -0.57
     Vor
    -0.56
     ber
    -0.56
     ser
    -0.56
     aus
    -0.56
     Bur
    -0.54
    POSITIVE LOGITS
     greateſt
    0.75
     typology
    0.73
     Shakspeare
    0.72
     pleaſure
    0.71
     Cæsar
    0.70
     Hift
    0.69
     quarries
    0.69
     generality
    0.69
     Escolar
    0.68
     itſelf
    0.67
    Activations Density 7.125%

    No Known Activations