© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210036
    Prev
    Next
    INDEX
    Explanations

    Gries, gris, griot

    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_5_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
     It
    0.64
    ۹
    0.64
    ۴
    0.62
    ۱
    0.59
    Б
    0.56
    １
    0.54
    ۵
    0.50
    мес
    0.50
    клад
    0.50
    ə
    0.49
    POSITIVE LOGITS
    ية
    0.60
    2
    0.55
    dır
    0.54
    a
    0.51
    ized
    0.49
     depolar
    0.48
    াশ
    0.47
    ící
    0.45
     který
    0.45
     safeguard
    0.44
    Activations Density 0.001%

    No Known Activations