© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23779
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    OnFile
    0.46
     على
    0.43
    퓨
    0.36
     촬영
    0.36
     “.
    0.35
     snee
    0.35
     інте
    0.35
    肩
    0.35
     जिल्हा
    0.35
    議論
    0.35
    POSITIVE LOGITS
    던
    0.69
     있던
    0.52
    하던
    0.50
     Crescent
    0.39
    ைகளைப்
    0.38
    லைப்
    0.37
     L
    0.35
     كان
    0.35
    జీ
    0.35
    łów
    0.35
    Activations Density 0.000%

    No Known Activations