© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180285
    Prev
    Next
    INDEX
    Explanations

    deleted, deletedAt, soft deletes

    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_24_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
     или
    0.41
    iyeti
    0.39
     અથવા
    0.37
    '";
    0.37
    wisdom
    0.36
    اليا
    0.36
    ដូច្ន
    0.36
    ವಾದ
    0.36
     ប៉ុ
    0.36
     또는
    0.35
    POSITIVE LOGITS
    追踪
    0.43
     scr
    0.39
    Prairie
    0.39
     Prairie
    0.38
     Nichols
    0.38
     prairie
    0.37
    ۃ
    0.37
    联邦
    0.37
     כש
    0.37
     trữ
    0.37
    Activations Density 0.000%

    No Known Activations