© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197291
    Prev
    Next
    INDEX
    Explanations

    audience

    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_4_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
    </b>
    0.91
    </h3>
    0.88
    ро
    0.85
    Z
    0.83
    اد
    0.82
    くて
    0.82
    ação
    0.81
    <0x0D>
    0.80
    ின்
    0.80
    ادا
    0.79
    POSITIVE LOGITS
    the
    1.16
    if
    1.01
    ă
    0.94
    for
    0.88
    was
    0.86
    বে
    0.83
     énorm
    0.82
    見積
    0.82
    ra
    0.81
    .
    0.79
    Activations Density 0.002%

    No Known Activations