© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31005
    Prev
    Next
    INDEX
    Explanations

    car models and specs

    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_40_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
     граф
    0.43
     artifact
    0.41
     గ్రా
    0.39
    artifacts
    0.39
    ']));
    0.37
     isle
    0.37
     artefact
    0.36
    credentials
    0.36
    숱
    0.36
     купа
    0.35
    POSITIVE LOGITS
     FID
    0.41
    ANS
    0.39
    建筑
    0.39
     ANS
    0.39
     FU
    0.39
     FLY
    0.39
    NORM
    0.39
     Lighting
    0.38
     Pap
    0.38
    FID
    0.38
    Activations Density 0.011%

    No Known Activations