© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211077
    Prev
    Next
    INDEX
    Explanations

    amaran, angur, rain

    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_5_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
     σε
    0.41
     في
    0.39
     in
    0.34
     школа
    0.34
    ໃນ
    0.33
    もら
    0.32
    在
    0.32
    <0xA8>
    0.32
    ți
    0.32
    ও
    0.32
    POSITIVE LOGITS
    З
    0.47
    ors
    0.46
    тся
    0.45
    Τ
    0.44
    یس
    0.43
    A
    0.42
    ته
    0.38
    지만
    0.37
    ل
    0.37
    ها
    0.37
    Activations Density 0.000%

    No Known Activations