© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133981
    Prev
    Next
    INDEX
    Explanations

    wo/we followed by specific completions

    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_1_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
    א
    1.48
    ).
    1.44
    。
    1.20
    。\
    1.10
    יות
    1.09
    ט
    1.08
    );
    1.05
    。,
    1.05
    ।
    1.04
    ).\\
    1.02
    POSITIVE LOGITS
    -
    1.38
    1
    1.07
     dụng
    1.00
     (
    0.99
    ного
    0.96
    uée
    0.95
     spectacularly
    0.93
    んですね
    0.93
    The
    0.92
     лица
    0.92
    Activations Density 0.000%

    No Known Activations