© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89493
    Prev
    Next
    INDEX
    Explanations

    font settings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     Sort
    0.44
     আমলে
    0.43
    .",
    0.43
    .".
    0.43
     Synt
    0.42
     strada
    0.41
    ."'
    0.41
    .$,
    0.40
     "".
    0.40
     Soares
    0.40
    POSITIVE LOGITS
    for
    0.54
    with
    0.47
    at
    0.46
     with
    0.45
    -*
    0.44
    il
    0.44
    ized
    0.41
    one
    0.41
    ties
    0.41
    izing
    0.40
    Activations Density 0.000%

    No Known Activations