© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83849
    Prev
    Next
    INDEX
    Explanations

    % Complete

    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_0_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
    "
    0.53
    -
    0.50
    \
    0.49
    filepath
    0.48
    lines
    0.45
    licer
    0.45
    amines
    0.45
     Sempre
    0.44
    )
    0.44
    pendiente
    0.42
    POSITIVE LOGITS
    م
    0.58
    м
    0.56
    вропей
    0.52
    Charging
    0.52
     чого
    0.50
     शिलालेख
    0.50
    కె
    0.49
     επ
    0.49
    କୁ
    0.49
     архе
    0.48
    Activations Density 0.000%

    No Known Activations