© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61294
    Prev
    Next
    INDEX
    Explanations

    *Br*, *fre*, *pre*, *tre* followed by Portuguese endings

    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_2_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
     of
    1.23
    ز
    1.12
     for
    1.07
    .
    1.05
    (
    1.05
    <0x0D>
    0.95
    으로
    0.87
     on
    0.86
    </h2>
    0.85
    </td>
    0.82
    POSITIVE LOGITS
    al
    1.06
    and
    1.05
    end
    0.96
    andran
    0.87
    N
    0.86
    ھی
    0.85
    entie
    0.84
     and
    0.83
    ல்
    0.82
    ال
    0.82
    Activations Density 0.000%

    No Known Activations