© 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. 112983
    Prev
    Next
    INDEX
    Explanations

    enlist help

    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
     as
    2.09
     are
    1.59
     will
    1.17
    يل
    1.16
    u
    1.13
     can
    1.08
    ↵
    1.07
    ↵↵
    1.02
    ták
    1.02
     是
    1.00
    POSITIVE LOGITS
    :
    1.58
    P
    1.45
    Z
    1.38
    H
    1.37
    는
    1.35
    /
    1.33
    I
    1.27
    W
    1.19
    Q
    1.16
    ك
    1.16
    Activations Density 0.000%

    No Known Activations