© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249741
    Prev
    Next
    INDEX
    Explanations

    technical and regional contexts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     tyrannical
    0.39
     पढ़ते
    0.38
     школова
    0.38
     दोग
    0.38
    iyê
    0.38
     دست
    0.36
     dependable
    0.36
     ^{\
    0.36
    _$
    0.36
     ^
    0.35
    POSITIVE LOGITS
    ph
    0.36
     เธอ
    0.35
    ১৯
    0.35
    inside
    0.35
    through
    0.34
     making
    0.34
    彼女
    0.34
    Bolt
    0.34
    me
    0.34
    profile
    0.34
    Activations Density 0.000%

    No Known Activations