© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151757
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers

    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_23_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
     செயற்ப
    0.16
    🍕
    0.14
    ₵
    0.13
    ℞
    0.13
    drawiam
    0.13
    税込
    0.13
    🪙
    0.13
    ʷ
    0.13
     टीमों
    0.13
    안
    0.13
    POSITIVE LOGITS
     $\
    0.14
     The
    0.13
     cue
    0.13
     Fans
    0.13
     US
    0.12
     la
    0.12
     vanity
    0.12
     SOA
    0.12
     smudge
    0.12
     These
    0.12
    Activations Density 0.001%

    No Known Activations