© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205578
    Prev
    Next
    INDEX
    Explanations

    course structure and objectives

    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_25_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
    機器
    0.44
    prop
    0.43
    residual
    0.40
    responses
    0.39
     ship
    0.39
    Rb
    0.39
    蒸
    0.38
    ([(
    0.38
    рку
    0.37
    残
    0.37
    POSITIVE LOGITS
     agenda
    0.40
     Giuliani
    0.40
     entrée
    0.40
     incluir
    0.39
     plein
    0.38
    芡
    0.38
     convers
    0.37
     handlebars
    0.37
     Havana
    0.37
     MotoGP
    0.37
    Activations Density 0.001%

    No Known Activations