© 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. 108669
    Prev
    Next
    INDEX
    Explanations

    blitz

    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
    <0xBE>
    1.14
    padă
    1.14
    ür
    1.13
    ٤
    1.09
    ٦
    1.01
    posição
    1.00
    ționale
    1.00
     ممكن
    0.99
    Avec
    0.97
    toare
    0.96
    POSITIVE LOGITS
     by
    1.72
    0
    1.45
     at
    1.43
     and
    1.38
     as
    1.37
    I
    1.29
     for
    1.23
     was
    1.20
    "
    1.20
     about
    1.09
    Activations Density 0.000%

    No Known Activations