© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78935
    Prev
    Next
    INDEX
    Explanations

    CZ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ك
    1.59
    E
    1.55
    Y
    1.43
    S
    1.42
    Z
    1.42
    M
    1.35
    T
    1.30
    Os
    1.29
    D
    1.26
    EN
    1.23
    POSITIVE LOGITS
    '
    1.91
     as
    1.83
     are
    1.75
    </h2>
    1.72
    ‘
    1.52
     americ
    1.48
    <0x0D>
    1.45
    ী
    1.44
    “
    1.40
    ha
    1.38
    Activations Density 0.004%

    No Known Activations