© 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. 200754
    Prev
    Next
    INDEX
    Explanations

    wargame and wargaming

    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
    g
    0.86
    h
    0.85
    <unused1827>
    0.84
            
    0.83
     loạn
    0.83
    alysis
    0.82
     realiz
    0.81
     fromi
    0.80
     Schottky
    0.80
    \
    0.80
    POSITIVE LOGITS
    ف
    1.14
    ید
    1.03
    s
    0.90
    تی
    0.84
    یت
    0.80
    .
    0.77
    ных
    0.76
    وس
    0.75
    </u>
    0.73
    ش
    0.73
    Activations Density 0.000%

    No Known Activations