© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161268
    Prev
    Next
    INDEX
    Explanations

    security posture management

    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_2_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
    이었
    1.55
    이었다
    1.16
    بود
    1.10
    
    1.08
     sèche
    1.02
    お店
    0.96
    だろう
    0.95
    ۳
    0.95
     않았
    0.95
    大海
    0.95
    POSITIVE LOGITS
    на
    1.59
    a
    1.45
    я
    1.30
    ست
    1.27
    ia
    1.25
     a
    1.21
    را
    1.20
    ла
    1.14
    า
    1.13
    et
    1.12
    Activations Density 0.001%

    No Known Activations