© 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. 141999
    Prev
    Next
    INDEX
    Explanations

    nbformat and nbextensions

    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
    й
    1.39
     pharmacokinetic
    1.32
    یت
    1.28
     ferromagnetic
    1.28
     ک
    1.26
    ِی
    1.23
    ய்
    1.22
    ;
    1.22
    می
    1.20
    یم
    1.18
    POSITIVE LOGITS
    గా
    1.71
    లో
    1.68
    কে
    1.59
    ام
    1.48
    에
    1.39
    de
    1.36
    中
    1.34
    cs
    1.32
    f
    1.30
    ty
    1.26
    Activations Density 0.000%

    No Known Activations