© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126053
    Prev
    Next
    INDEX
    Explanations

    cricket team, stadium, league, ball, fan, match, cup

    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_3_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
     seiner
    0.63
    </b>
    0.59
     ";
    0.59
     deft
    0.57
     regula
    0.57
     pisan
    0.57
     gusto
    0.56
    ".
    0.55
    F
    0.55
     significant
    0.55
    POSITIVE LOGITS
    gun
    0.76
    ka
    0.73
    dens
    0.71
    crow
    0.70
    gain
    0.68
    drying
    0.68
    cbc
    0.68
    ation
    0.67
    ks
    0.66
    dat
    0.66
    Activations Density 0.000%

    No Known Activations