© 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. 231773
    Prev
    Next
    INDEX
    Explanations

    robocopy, acid, Thai script

    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
    >
    0.81
    0
    0.78
    ?
    0.68
     et
    0.67
    ,”
    0.67
     искусства
    0.64
     It
    0.63
    terna
    0.63
    orca
    0.63
    .
    0.63
    POSITIVE LOGITS
    在
    1.16
    ة
    1.12
    ও
    1.09
    ing
    1.04
    も
    1.02
    িন
    1.01
    ين
    1.01
    a
    0.99
    ın
    0.95
    un
    0.94
    Activations Density 0.000%

    No Known Activations