© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202842
    Prev
    Next
    INDEX
    Explanations

    Address followed by details

    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_12_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
    ز
    0.51
    مه
    0.51
    踰
    0.50
     دو
    0.50
     Fmat
    0.50
     trội
    0.50
    ونز
    0.49
    檄
    0.49
    蛯
    0.49
     Verteid
    0.49
    POSITIVE LOGITS
    p
    0.61
    ity
    0.57
    ink
    0.55
    aker
    0.54
    art
    0.54
    don
    0.54
    ITY
    0.53
    are
    0.53
     be
    0.52
    ooky
    0.52
    Activations Density 0.001%

    No Known Activations