© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133965
    Prev
    Next
    INDEX
    Explanations

    management and security technologies

    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_6_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
    은
    1.28
    the
    1.27
    -
    1.11
    ing
    1.02
    ı
    1.02
    he
    1.00
     .
    0.99
    å
    0.99
    1
    0.98
    ны
    0.97
    POSITIVE LOGITS
    د
    1.49
    ד
    1.49
     persiste
    1.19
    ل
    1.18
    ל
    1.12
    غیر
    1.09
     ομά
    1.08
     bactéri
    1.08
     гульнявыя
    1.05
    ر
    1.05
    Activations Density 0.056%

    No Known Activations