© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4735
    Prev
    Next
    INDEX
    Explanations

    define and training loop

    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_40_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
    wiata
    0.44
     harvested
    0.42
     harvesting
    0.39
     spraying
    0.38
    亡
    0.38
    rement
    0.38
    ঊ
    0.38
     fools
    0.37
     baked
    0.37
    विद्या
    0.37
    POSITIVE LOGITS
     परिभाषित
    0.46
    定義
    0.41
    ]=[
    0.40
     Cull
    0.40
     define
    0.39
    फ़
    0.39
    Define
    0.39
     Chis
    0.38
     Define
    0.38
     definir
    0.38
    Activations Density 0.000%

    No Known Activations