© 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. 58758
    Prev
    Next
    INDEX
    Explanations

    vpc, DFC

    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
    在
    1.51
     καθώς
    1.20
     in
    1.17
    la
    1.15
     σε
    1.06
     tän
    1.04
    も
    1.01
     در
    1.00
    \}.
    0.99
    و
    0.98
    POSITIVE LOGITS
    ية
    1.23
    ون
    1.19
    1.16
     and
    1.13
    t
    1.03
     (
    1.02
    ist
    1.02
     for
    1.01
     For
    0.97
     It
    0.96
    Activations Density 0.000%

    No Known Activations