© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75724
    Prev
    Next
    INDEX
    Explanations

    look followed by in or at or down

    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_31_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
     aid
    0.39
     看
    0.38
     clashes
    0.38
     gibi
    0.36
     geï
    0.36
     Aid
    0.36
     బంగ
    0.35
     ог
    0.35
    Neil
    0.35
     конфлик
    0.35
    POSITIVE LOGITS
    残念
    0.41
    calend
    0.40
    Calend
    0.39
    运
    0.38
    Union
    0.37
    Pipe
    0.37
    intermedi
    0.36
    칩
    0.36
    Prod
    0.36
     pipe
    0.36
    Activations Density 0.002%

    No Known Activations