© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81048
    Prev
    Next
    INDEX
    Explanations

    Ти, Era, jaja, сленг

    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_0_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
    un
    1.53
    ル
    1.50
    AN
    1.48
    ل
    1.38
    ма
    1.34
    It
    1.33
    ра
    1.30
    AR
    1.30
    Y
    1.28
    ２
    1.28
    POSITIVE LOGITS
    -
    1.53
     with
    1.48
    تين
    1.45
    ς
    1.41
     by
    1.32
     (
    1.31
    ться
    1.30
    تان
    1.26
     not
    1.23
     when
    1.22
    Activations Density 0.000%

    No Known Activations