© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156628
    Prev
    Next
    INDEX
    Explanations

    Slavic 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_50_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
    žení
    0.45
    ління
    0.42
     тела
    0.42
    zeni
    0.41
    жений
    0.40
    чений
    0.40
    ření
    0.40
    ભ
    0.40
    жению
    0.38
    žen
    0.38
    POSITIVE LOGITS
     ricon
    0.43
    اسة
    0.40
    㜿
    0.40
     prata
    0.40
    पुट
    0.39
     rato
    0.39
     rat
    0.38
     ratt
    0.38
    nością
    0.38
    出発
    0.37
    Activations Density 0.000%

    No Known Activations