© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167365
    Prev
    Next
    INDEX
    Explanations

    prior to contract

    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_34_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
     pubb
    0.36
     Suprema
    0.35
    挀
    0.35
    ณ
    0.35
    flows
    0.34
     stints
    0.34
    czych
    0.34
    .??.??"]
    0.34
     Cedex
    0.33
     χώ
    0.33
    POSITIVE LOGITS
    ueur
    0.50
     cắt
    0.43
     cutter
    0.42
     DISPLAY
    0.41
     props
    0.39
    ものの
    0.38
     Verdana
    0.37
    닿
    0.37
     melawan
    0.37
     испы
    0.37
    Activations Density 0.004%

    No Known Activations