© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244023
    Prev
    Next
    INDEX
    Explanations

    integrity impact protection

    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_40_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
    Ba
    0.38
    racellular
    0.38
     cerebrospinal
    0.37
    ;%%
    0.37
     Address
    0.37
     Ba
    0.36
    েশ্বর
    0.36
    骖
    0.36
    閉じ
    0.36
     Cong
    0.35
    POSITIVE LOGITS
     brun
    0.41
    حة
    0.39
     bonnes
    0.39
    orea
    0.38
    iume
    0.36
    ラン
    0.35
     jää
    0.35
     никто
    0.35
    ụng
    0.35
    maze
    0.34
    Activations Density 0.001%

    No Known Activations