© 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. 143063
    Prev
    Next
    INDEX
    Explanations

    enforcers

    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
     \
    1.48
     It
    1.43
    .
    1.34
    ized
    1.25
    我
    1.22
    就
    1.17
    1.09
     There
    1.09
     panahon
    1.07
    ことです
    1.06
    POSITIVE LOGITS
    কে
    2.05
    та
    1.68
    ה
    1.66
    на
    1.58
    ের
    1.55
    s
    1.54
    ти
    1.48
    ു
    1.48
    the
    1.46
    ን
    1.45
    Activations Density 0.000%

    No Known Activations