© 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. 217652
    Prev
    Next
    INDEX
    Explanations

    database credentials

    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_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
    target
    0.42
     targets
    0.41
     target
    0.38
     impressed
    0.37
    targets
    0.36
    용
    0.34
    name
    0.34
    Tour
    0.34
    ilon
    0.33
    Sys
    0.33
    POSITIVE LOGITS
    याच्या
    0.43
     белару
    0.42
    蝴
    0.41
    चारियों
    0.41
     buttonAnimation
    0.40
     insuffisamment
    0.39
     Salaries
    0.39
     Balashov
    0.39
    渠
    0.39
     Macintosh
    0.38
    Activations Density 0.002%

    No Known Activations