© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 105274
    Prev
    Next
    INDEX
    Explanations

    Russian adjective endings

    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_1_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
    s
    1.56
    n
    1.48
    ség
    1.35
    ስ
    1.28
     for
    1.27
     to
    1.26
    ut
    1.26
    w
    1.16
     from
    1.16
    ag
    1.15
    POSITIVE LOGITS
    하다
    1.23
    이가
    1.23
    ل
    1.22
    ้น
    1.13
    もら
    1.13
    お
    1.13
    ریان
    1.05
    食べ
    1.03
    買う
    1.02
    見た
    1.01
    Activations Density 0.001%

    No Known Activations