© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122431
    Prev
    Next
    INDEX
    Explanations

    border-bottom, collapse

    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_37_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
     అవకాశం
    0.38
    Southeast
    0.36
    ুয়ার
    0.36
     nho
    0.36
     bbox
    0.36
     bunting
    0.36
    봉
    0.36
     morgen
    0.36
     بۆ
    0.35
    विव
    0.35
    POSITIVE LOGITS
     see
    0.48
     Holl
    0.43
     perme
    0.41
    see
    0.41
     µ
    0.39
     McGee
    0.38
     contends
    0.38
     perv
    0.38
    ែ
    0.38
     See
    0.37
    Activations Density 0.000%

    No Known Activations