© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161978
    Prev
    Next
    INDEX
    Explanations

    yaoi, consum, submit, sac, col, met, ser, wolf

    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_2_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
    ق
    0.71
     on
    0.64
    im
    0.57
    ote
    0.57
    Radius
    0.56
    Have
    0.55
    ud
    0.53
    ?
    0.53
    at
    0.52
     einzigen
    0.52
    POSITIVE LOGITS
    та
    0.91
    含ま
    0.69
    re
    0.66
     tiresome
    0.65
     soiled
    0.64
    ۔
    0.64
    りは
    0.61
     supremely
    0.60
    ir
    0.59
    りたい
    0.59
    Activations Density 0.022%

    No Known Activations