© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106099
    Prev
    Next
    INDEX
    Explanations

    suffix "-er" or "-ace" or "-cess"

    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_1_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
    am
    1.45
    im
    1.40
    c
    1.34
    ir
    1.13
    ak
    1.13
    ang
    1.12
    a
    1.05
    are
    1.04
    行う
    1.03
    dynamics
    1.01
    POSITIVE LOGITS
    <0x80>
    1.34
    D
    1.20
    લ
    1.16
    L
    1.05
    <0x85>
    1.02
    ęła
    1.01
    تي
    1.00
    ého
    0.99
    是
    0.99
    ล
    0.99
    Activations Density 0.001%

    No Known Activations