© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140864
    Prev
    Next
    INDEX
    Explanations

    user details

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     P
    0.49
     MCU
    0.46
    isque
    0.45
     p
    0.44
    ീസ്
    0.42
     prismatic
    0.39
     Clifford
    0.38
    mcs
    0.38
     ferric
    0.38
    <0x89>
    0.37
    POSITIVE LOGITS
    ร้าย
    0.42
     rých
    0.38
    toupper
    0.37
    ksam
    0.36
     rych
    0.36
    秒
    0.35
     быстрее
    0.35
     rehearse
    0.34
    xam
    0.33
    臺
    0.33
    Activations Density 0.015%

    No Known Activations