© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43489
    Prev
    Next
    INDEX
    Explanations

    Qualcomm, spread spectrum, Hadamard matrix

    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_13_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
     ___
    0.47
    )',
    0.46
    ちなみに
    0.46
    」，
    0.45
     __
    0.44
    ゾーン
    0.43
     хими
    0.42
     できる
    0.42
    뎀
    0.41
    воз
    0.41
    POSITIVE LOGITS
     bro
    0.50
     c
    0.46
    elé
    0.46
     slapped
    0.45
    OU
    0.45
    ZIE
    0.44
    LU
    0.43
    UE
    0.43
     dou
    0.43
     BRO
    0.43
    Activations Density 0.017%

    No Known Activations