© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11814
    Prev
    Next
    INDEX
    Explanations

    1 followed by comma

    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_40_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
    鋐
    0.41
     denote
    0.40
     ഭാര്യ
    0.38
     ஜீ
    0.38
     Buildable
    0.37
     tucked
    0.37
     läuft
    0.37
     😂😂
    0.37
    stocked
    0.36
     stocked
    0.36
    POSITIVE LOGITS
     Naf
    0.40
     Paragu
    0.37
    ociação
    0.37
    )[:,
    0.36
    Pol
    0.36
     민
    0.36
     Prec
    0.36
    సై
    0.36
     финансо
    0.35
    Prec
    0.35
    Activations Density 0.001%

    No Known Activations