© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 232220
    Prev
    Next
    INDEX
    Explanations

    ganondorf

    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_6_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
    st
    0.62
    as
    0.56
    น่า
    0.56
    ק
    0.54
    d
    0.53
    .
    0.51
     tuner
    0.50
    :
    0.50
    ด
    0.49
    weiter
    0.49
    POSITIVE LOGITS
     vínculos
    0.66
     és
    0.65
     كانت
    0.65
     muestras
    0.64
     mãos
    0.64
     إ
    0.64
     было
    0.64
     كان
    0.63
     νέ
    0.63
     pessoas
    0.63
    Activations Density 0.000%

    No Known Activations