© 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. 108794
    Prev
    Next
    INDEX
    Explanations

    sea, inn, chamber, lanes, Ida, Ba

    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
    il
    1.38
    un
    1.27
    い
    1.19
    ਰ
    1.10
    ul
    1.09
    as
    1.06
    ographic
    1.04
    on
    1.03
    ți
    1.02
    in
    0.98
    POSITIVE LOGITS
    s
    1.35
    0
    1.35
    9
    1.27
    8
    1.27
    6
    1.23
    j
    1.20
    3
    1.17
    7
    1.15
    4
    1.11
    5
    1.09
    Activations Density 0.001%

    No Known Activations