© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 139069
    Prev
    Next
    INDEX
    Explanations

    pleading guilty

    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_37_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
     სახ
    0.41
    Sens
    0.39
     вопро
    0.38
    ધાનસભા
    0.36
    Region
    0.35
    PlatformTarget
    0.35
    GAG
    0.35
     理
    0.35
    Ignoring
    0.35
     ಪ್ರ
    0.34
    POSITIVE LOGITS
     defendants
    0.51
     अभियुक्त
    0.44
     confess
    0.43
     Defendants
    0.42
     prosecutors
    0.41
    させて頂きます
    0.40
     avec
    0.40
     mengaku
    0.40
    dengan
    0.39
     confesses
    0.39
    Activations Density 0.000%

    No Known Activations