© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1437
    Prev
    Next
    INDEX
    Explanations

    arXiv papers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    avais
    0.39
    র্কের
    0.39
     melting
    0.39
     Outside
    0.38
    癲
    0.38
     melts
    0.37
     Promoter
    0.37
    ப்படு
    0.37
    隽
    0.37
    слан
    0.37
    POSITIVE LOGITS
    FT
    0.40
    زى
    0.40
     Brou
    0.37
     discriminate
    0.37
     Nucleaire
    0.37
    ﻡ
    0.37
    ޒ
    0.36
     rub
    0.36
    eft
    0.36
    Доб
    0.36
    Activations Density 0.000%

    No Known Activations