© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 237102
    Prev
    Next
    INDEX
    Explanations

    and followed by a name or letter

    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_32_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
    戀
    0.44
    batis
    0.43
     Percol
    0.43
     Color
    0.40
     ২৬
    0.40
     цвет
    0.39
     Farbe
    0.39
     పూర్తిగా
    0.39
     COLOR
    0.39
    恋
    0.38
    POSITIVE LOGITS
     équip
    0.37
     averages
    0.37
    groups
    0.36
     statistic
    0.36
     naš
    0.36
     jind
    0.35
     profiles
    0.34
     casings
    0.34
     mother
    0.34
     mathematical
    0.34
    Activations Density 0.003%

    No Known Activations