© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83906
    Prev
    Next
    INDEX
    Explanations

    saponification, javascript, saga

    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
    ia
    1.66
    t
    1.55
    ing
    1.37
     I
    1.37
    ্য
    1.26
    ो
    1.24
    ang
    1.18
    ee
    1.18
     de
    1.16
    us
    1.16
    POSITIVE LOGITS
    ي
    2.14
    ه
    2.11
    ث
    1.65
    н
    1.63
    an
    1.59
    ი
    1.55
    ה
    1.55
    ان
    1.52
    י
    1.45
    य
    1.39
    Activations Density 0.000%

    No Known Activations