© 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. 106201
    Prev
    Next
    INDEX
    Explanations

    Danube, Denhardt, Donauinsel, Ben-Hur

    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
    h
    1.62
    1
    1.34
    ec
    1.30
    c
    1.29
    m
    1.28
    t
    1.24
    z
    1.23
    ar
    1.20
    g
    1.17
    x
    1.17
    POSITIVE LOGITS
    ，
    1.47
    ،
    1.14
    1.12
    ：
    1.09
    서
    1.09
    、
    1.06
    </h3>
    1.04
    う
    1.02
    มัน
    1.01
     व
    0.97
    Activations Density 0.000%

    No Known Activations