© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153112
    Prev
    Next
    INDEX
    Explanations

    `:type` followed by type hints

    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_23_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
    haba
    0.26
     ভাইস
    0.24
    ॥
    0.23
    ூ
    0.22
    Ment
    0.22
     पग
    0.22
     Harrington
    0.22
    שית
    0.21
     샤
    0.21
    【
    0.21
    POSITIVE LOGITS
     '')
    0.27
    एएस
    0.26
     ^{\
    0.25
     ').
    0.25
     हटाने
    0.25
     berlin
    0.25
     richtig
    0.24
     univ
    0.24
     Игра
    0.24
     социально
    0.23
    Activations Density 0.008%

    No Known Activations