© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82392
    Prev
    Next
    INDEX
    Explanations

    Polish word endings

    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_53_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
    ޟ
    0.46
    秝
    0.40
    uvi
    0.40
     चाहि
    0.39
     blem
    0.39
     బి
    0.39
    اض
    0.38
    仴
    0.38
    ᴍ
    0.38
    Ū
    0.38
    POSITIVE LOGITS
    ś
    0.48
    ry
    0.43
    yny
    0.41
    niają
    0.40
    ety
    0.39
    owały
    0.39
    ены
    0.39
    że
    0.38
    alary
    0.38
     skład
    0.37
    Activations Density 0.000%

    No Known Activations