© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39785
    Prev
    Next
    INDEX
    Explanations

    it was

    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
     ข้อ
    0.59
     devoted
    0.56
    IST
    0.55
    a
    0.55
     sill
    0.55
     distributed
    0.54
     substituted
    0.54
     merging
    0.54
    ult
    0.54
     cotton
    0.53
    POSITIVE LOGITS
    О
    0.70
    С
    0.69
    Т
    0.67
    ",
    0.66
    Ко
    0.65
    codiles
    0.63
    C
    0.62
    При
    0.61
    До
    0.61
    hões
    0.58
    Activations Density 0.010%

    No Known Activations