© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137520
    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_12_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
     SWE
    0.56
     categor
    0.55
     Sweater
    0.54
    （
    0.53
     Soap
    0.50
     unlock
    0.50
    ূত
    0.50
     rea
    0.49
    SWE
    0.49
     direcciones
    0.49
    POSITIVE LOGITS
    少なくとも
    0.59
     investimento
    0.57
    ษ
    0.57
     سيكون
    0.57
     божомолу
    0.55
    bhl
    0.55
    բ
    0.53
     фаразы
    0.52
    ṕ
    0.52
    嬰
    0.52
    Activations Density 0.000%

    No Known Activations