© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46152
    Prev
    Next
    INDEX
    Explanations

    ; followed by class

    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_10_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
     کریں۔
    0.56
    elevationMap
    0.55
    专题
    0.55
    か
    0.54
     ajuta
    0.54
    assaytype
    0.54
    in
    0.53
     incó
    0.52
    dataPro
    0.52
    azioni
    0.52
    POSITIVE LOGITS
    (
    0.66
    ence
    0.61
    를
    0.56
    ivism
    0.54
    amp
    0.53
     ن
    0.53
    i
    0.52
     molecule
    0.51
     s
    0.51
     بر
    0.51
    Activations Density 0.005%

    No Known Activations