© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14124
    Prev
    Next
    INDEX
    Explanations

    donned his

    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_13_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
    m
    0.65
    idents
    0.60
    mts
    0.57
    t
    0.55
    _
    0.54
    Liam
    0.54
    D
    0.54
    ﺠ
    0.54
    Drake
    0.54
    iet
    0.52
    POSITIVE LOGITS
    ри
    0.68
     conjugated
    0.61
     мали
    0.61
     kembali
    0.59
     clarified
    0.59
     Alibaba
    0.58
     catatan
    0.57
     EPO
    0.56
     contoh
    0.55
     chalkboard
    0.55
    Activations Density 0.005%

    No Known Activations