© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32556
    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_31_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
    $+
    0.44
    inging
    0.40
     $+
    0.39
    дование
    0.38
     때는
    0.37
     दिलों
    0.37
    崂
    0.37
     요즘
    0.36
     बोलो
    0.36
     решение
    0.36
    POSITIVE LOGITS
     naz
    0.48
     Lask
    0.39
     Naz
    0.39
    naz
    0.39
     nid
    0.37
    Naz
    0.36
     күз
    0.35
     recur
    0.35
    wamy
    0.35
     compresses
    0.35
    Activations Density 0.000%

    No Known Activations