© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42903
    Prev
    Next
    INDEX
    Explanations

    file operations

    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_22_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
    AG
    0.46
    SH
    0.46
    AGG
    0.42
    ANG
    0.41
     لطف
    0.41
    ADD
    0.41
     SH
    0.40
    全
    0.40
    Family
    0.40
    )(\
    0.40
    POSITIVE LOGITS
    ்களில்
    0.46
     многие
    0.43
     bloke
    0.43
    කය
    0.42
    ड़ियां
    0.42
     investigative
    0.41
     chicago
    0.41
    ጲ
    0.41
     ብዙ
    0.41
     অধ্যাপ
    0.40
    Activations Density 0.000%

    No Known Activations