© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39107
    Prev
    Next
    INDEX
    Explanations

    PIL import Image

    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_3_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
    n
    1.60
    in
    1.10
    f
    1.04
    a
    0.92
    لى
    0.91
    ir
    0.89
    ne
    0.85
    ن
    0.82
    z
    0.82
    न
    0.82
    POSITIVE LOGITS
    к
    0.91
    行う
    0.84
     отношения
    0.76
    т
    0.74
    ある
    0.70
     дизай
    0.70
     councillor
    0.69
    ेयर
    0.69
    ри
    0.68
     ось
    0.68
    Activations Density 0.006%

    No Known Activations