© 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. 10984
    Prev
    Next
    INDEX
    Explanations

    time complexity O(n)

    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
    ammad
    0.27
    ৩৯
    0.27
     square
    0.26
     vector
    0.26
    square
    0.26
     sei
    0.25
     \|
    0.25
    第九
    0.25
    }\|
    0.25
    itable
    0.25
    POSITIVE LOGITS
     autocomplete
    0.27
     CONS
    0.25
     IGN
    0.24
    <unused552>
    0.24
     gorilla
    0.24
     தக்க
    0.24
    不断的
    0.23
    addChild
    0.23
     कैलो
    0.23
     CONTRIBUTORS
    0.23
    Activations Density 0.014%

    No Known Activations