© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 85310
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     उन्‍हें
    0.45
    tembre
    0.41
    senal
    0.40
    ップ
    0.39
    Novel
    0.37
    ཌ
    0.37
     महत्व
    0.37
     সম্পর্কের
    0.37
    )}-
    0.36
    Tail
    0.36
    POSITIVE LOGITS
     made
    0.47
     green
    0.47
     alphabetical
    0.44
     June
    0.43
     swimming
    0.42
     resa
    0.42
     renovation
    0.42
     soaking
    0.42
     hot
    0.42
     planned
    0.41
    Activations Density 0.000%

    No Known Activations