© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11504
    Prev
    Next
    INDEX
    Explanations

    verbs expressing aggression, crime, and theft, particularly in past tense

    oai_token-act-pair · gemini-2.0-flash

    violence, theft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    kloped
    -0.59
    <>());
    -0.58
    VersionUID
    -0.57
    AutoScaleMode
    -0.53
    visiae
    -0.51
     Cataloging
    -0.51
     intptr
    -0.50
     thiệu
    -0.49
    traceback
    -0.48
    <bos>
    -0.48
    POSITIVE LOGITS
    IntoConstraints
    0.57
    /**
    0.57
     pinulongan
    0.53
    ⓘ
    0.52
     Maren
    0.52
     Majefty
    0.51
     Cri
    0.47
     Bajos
    0.47
     reaſon
    0.47
     Vikipedi
    0.47
    Activations Density 1.416%

    No Known Activations