© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45935
    Prev
    Next
    INDEX
    Explanations

    box-shadow

    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_22_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
     Всем
    0.45
     expressly
    0.45
     Cappadocia
    0.44
     Umm
    0.43
     Odd
    0.41
     incidentally
    0.40
    шкин
    0.40
    싹
    0.40
     परिव
    0.39
     Polly
    0.39
    POSITIVE LOGITS
    chis
    0.46
     گار
    0.45
    kości
    0.41
    deco
    0.38
    NET
    0.38
    गु
    0.38
    >*</
    0.38
    nu
    0.38
     różne
    0.37
    kość
    0.37
    Activations Density 0.000%

    No Known Activations