© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223158
    Prev
    Next
    INDEX
    Explanations

    darting movement

    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
    \
    0.76
    eth
    0.70
    impinan
    0.68
    aria
    0.68
    als
    0.65
    enced
    0.64
    enu
    0.64
    सम्म
    0.63
    arg
    0.62
    acia
    0.62
    POSITIVE LOGITS
    s
    0.92
     can
    0.76
    0.75
    ж
    0.75
    _
    0.74
     may
    0.71
     ､
    0.70
     intranet
    0.68
     reproduce
    0.68
     tighten
    0.67
    Activations Density 0.001%

    No Known Activations