© 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. 134738
    Prev
    Next
    INDEX
    Explanations

    Wild Type

    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
    <0x0D>
    1.15
    이었
    0.98
    ็น
    0.96
    ;
    0.91
    ный
    0.89
     agacch
    0.89
    就没有
    0.87
    سل
    0.85
    िटी
    0.84
    وون
    0.84
    POSITIVE LOGITS
     is
    1.81
     on
    1.63
     to
    1.41
     are
    1.35
    is
    1.15
    리
    1.11
     at
    1.09
    bir
    1.04
    ü
    1.00
    大
    1.00
    Activations Density 0.000%

    No Known Activations