© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137644
    Prev
    Next
    INDEX
    Explanations

    programperiodlunchhomeroom

    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_12_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
     Фурга
    0.64
    हमने
    0.52
    8
    0.52
     doğrudan
    0.51
    芒果
    0.51
    城镇
    0.50
    일부터
    0.49
    基于
    0.49
     >=
    0.49
    আমরা
    0.48
    POSITIVE LOGITS
     C
    0.56
    ell
    0.53
     construction
    0.49
     Cree
    0.48
     termini
    0.47
    琨
    0.47
    ku
    0.46
    ütter
    0.46
    খন
    0.46
     traduce
    0.46
    Activations Density 0.000%

    No Known Activations