© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3644
    Prev
    Next
    INDEX
    Explanations

    words suggesting ongoing improvement

    oai_token-act-pair · gemini-2.0-flash

    improvement and progression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ########.
    -0.62
    NOPQRST
    -0.57
    SourceChecksum
    -0.52
    +#+#
    -0.47
    IntoConstraints
    -0.44
    InputBorder
    -0.44
    cy
    -0.43
     Sem
    -0.43
    vent
    -0.43
    tagHelperRunner
    -0.43
    POSITIVE LOGITS
     houſe
    0.75
     cdti
    0.69
     Efq
    0.65
     betweenstory
    0.62
     greateſt
    0.60
     itſelf
    0.57
     ſever
    0.57
     ſtand
    0.57
     faſt
    0.55
     Cæsar
    0.55
    Activations Density 14.281%

    No Known Activations