© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210494
    Prev
    Next
    INDEX
    Explanations

    police, helpline, authorities, office

    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_20_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
    خری
    0.44
     इजा
    0.41
     سعید
    0.41
    ,\,\
    0.41
    🪴
    0.40
    لية
    0.39
     plă
    0.39
    рея
    0.38
     deemed
    0.38
     работо
    0.38
    POSITIVE LOGITS
     प्रक्रियाओं
    0.46
    the
    0.41
     ಅವರ
    0.40
    ?»
    0.40
     અ
    0.39
     methods
    0.39
    IX
    0.39
     Methoden
    0.39
    ?),
    0.39
     philosophers
    0.39
    Activations Density 0.001%

    No Known Activations