© 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. 26240
    Prev
    Next
    INDEX
    Explanations

    crew members or mates

    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
    다면
    0.42
    et
    0.35
    ляє
    0.35
    ے
    0.34
    ныгы
    0.30
    C
    0.30
    icação
    0.28
    ంగ్
    0.28
    osť
    0.28
    。《
    0.28
    POSITIVE LOGITS
    IK
    0.31
     perished
    0.30
    tn
    0.29
    ne
    0.27
    ties
    0.27
    К
    0.26
     for
    0.26
     emitted
    0.26
     accorded
    0.26
     overridden
    0.26
    Activations Density 0.005%

    No Known Activations