© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39983
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     her
    0.98
     she
    0.96
     она
    0.95
     ей
    0.95
    她
    0.93
    彼女
    0.89
    她的
    0.88
     그녀
    0.86
     ఆమె
    0.85
    她在
    0.83
    POSITIVE LOGITS
     hun
    2.31
     тя
    2.19
    Hun
    2.06
     Hun
    2.02
     hon
    1.95
     Тя
    1.87
    hun
    1.76
     Hon
    1.66
    Hon
    1.63
    hon
    1.50
    Activations Density 0.000%

    No Known Activations