© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106869
    Prev
    Next
    INDEX
    Explanations

    vesper or vortex words

    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_1_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
    스가
    1.07
    정을
    1.03
     humains
    1.03
    야
    1.02
     impediments
    0.97
    ی
    0.96
    ের
    0.95
    یش
    0.95
    \}.
    0.94
    тся
    0.93
    POSITIVE LOGITS
    ↵↵
    1.50
     a
    1.34
    em
    1.32
    l
    1.32
     by
    1.30
    ли
    1.27
    "),
    1.25
    us
    1.20
    at
    1.18
    ij
    1.18
    Activations Density 0.001%

    No Known Activations