© 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. 16978
    Prev
    Next
    INDEX
    Explanations

    float, uint, vec in code

    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
    ycor
    0.38
    ティング
    0.36
    溆
    0.35
     Curr
    0.35
     hundert
    0.35
    xcor
    0.35
     khóa
    0.35
     সঞ্জীবনী
    0.35
     walk
    0.34
     breather
    0.34
    POSITIVE LOGITS
     व्यापक
    0.40
     ಅಮ
    0.40
     ventes
    0.40
    ចំណ
    0.40
    Sources
    0.39
    మణ
    0.39
     શોધ
    0.36
    芢
    0.35
     जीव
    0.35
     paired
    0.35
    Activations Density 0.003%

    No Known Activations