© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1440
    Prev
    Next
    INDEX
    Explanations

    bogged down

    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_39_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
    idth
    0.39
    ismar
    0.39
    ˩
    0.38
    ęż
    0.37
     çerçe
    0.37
    istisch
    0.37
    ämä
    0.35
    fdPar
    0.35
    (@"
    0.35
     isti
    0.35
    POSITIVE LOGITS
     Real
    0.36
     настоящего
    0.36
    的行为
    0.35
    qry
    0.35
     judicious
    0.35
    ểu
    0.34
     findAll
    0.34
    XA
    0.33
     jamming
    0.33
     rightly
    0.33
    Activations Density 0.044%

    No Known Activations