© 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. 137048
    Prev
    Next
    INDEX
    Explanations

    checking for empty or searching

    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_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
    بر
    0.53
    Adjustment
    0.53
     docked
    0.51
    Fiber
    0.51
    ِر
    0.51
    Instrumentation
    0.50
    뽀
    0.50
    6
    0.50
     state
    0.50
     truncation
    0.50
    POSITIVE LOGITS
    ాను
    0.59
    твы
    0.55
     осуществ
    0.54
     невозможно
    0.54
     основе
    0.53
     பெயரை
    0.53
    cannot
    0.52
     nossas
    0.52
    cidas
    0.52
     nosso
    0.52
    Activations Density 0.003%

    No Known Activations