© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37383
    Prev
    Next
    INDEX
    Explanations

    PDF files

    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_11_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
     问题
    0.52
     illum
    0.52
     tipo
    0.52
     vó
    0.52
     jeg
    0.50
     கிள
    0.50
    。
    0.49
     తర్వాత
    0.48
     parecen
    0.48
    䫝
    0.48
    POSITIVE LOGITS
    AP
    0.54
    IRA
    0.54
    ला
    0.52
    IB
    0.52
    ES
    0.51
    }=
    0.50
    Attribute
    0.50
    AS
    0.50
    IP
    0.50
    IG
    0.49
    Activations Density 0.005%

    No Known Activations