© 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. 28895
    Prev
    Next
    INDEX
    Explanations

    individual, body, mind, spirit, lion, lotus, moon

    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
     root
    0.44
     PERFECT
    0.43
     सिद्धि
    0.42
     Root
    0.42
     obstáculos
    0.40
     ROOT
    0.40
    Root
    0.40
     √
    0.40
     성공
    0.39
    Obst
    0.39
    POSITIVE LOGITS
    thebibliography
    0.41
     alterar
    0.41
    뉘
    0.38
    wyn
    0.37
    Eksterne
    0.37
     Сто
    0.37
     resetButton
    0.36
    Wyn
    0.35
     pej
    0.35
    鍒
    0.35
    Activations Density 0.019%

    No Known Activations