© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 138940
    Prev
    Next
    INDEX
    Explanations

    VRAM sufficient

    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_37_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
    ശം
    0.47
    utzer
    0.41
    ipse
    0.41
    uuid
    0.39
    ંટણી
    0.39
     Untersuch
    0.39
    ellt
    0.38
    纵
    0.38
    validation
    0.38
    発
    0.38
    POSITIVE LOGITS
     memory
    0.51
     memoria
    0.49
    Memory
    0.48
     Memory
    0.46
     memória
    0.46
    メモリ
    0.45
     V
    0.44
    memory
    0.43
     GD
    0.41
    Scrolling
    0.40
    Activations Density 0.008%

    No Known Activations