© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237788
    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_25_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
     연습
    0.47
     дово
    0.43
     cumprimento
    0.43
    렴
    0.43
     minh
    0.43
    слав
    0.42
     aans
    0.41
    )}^{\
    0.40
     thước
    0.40
     ১৯৬৫
    0.40
    POSITIVE LOGITS
    ela
    0.54
    OU
    0.51
    re
    0.49
     हैव
    0.49
    chemical
    0.49
    troop
    0.48
    enz
    0.48
    HO
    0.48
    de
    0.48
    era
    0.48
    Activations Density 0.000%

    No Known Activations