© 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. 130814
    Prev
    Next
    INDEX
    Explanations

    evil

    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
    ید
    0.82
    را
    0.77
    اد
    0.70
    )
    0.68
    ributing
    0.65
    க்கா
    0.65
    ang
    0.64
    uada
    0.64
    ripción
    0.64
    pering
    0.64
    POSITIVE LOGITS
    i
    1.14
    j
    1.13
    ज
    1.05
    ন
    1.01
    ال
    0.99
    ST
    0.98
     vuol
    0.96
     vuole
    0.96
    એ
    0.94
    ooo
    0.94
    Activations Density 0.001%

    No Known Activations