© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85915
    Prev
    Next
    INDEX
    Explanations

    Resist the urge

    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_18_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
    IsResolver
    0.27
    Ռ
    0.27
    澳大利
    0.27
    سٹم
    0.26
    Ⲣ
    0.26
    Theorem
    0.26
    DBMS
    0.25
     quantifier
    0.25
    Operand
    0.25
     spectrometry
    0.25
    POSITIVE LOGITS
     le
    0.29
    ⁹
    0.28
     עם
    0.28
     with
    0.27
     и
    0.27
    움을
    0.26
     a
    0.25
     the
    0.25
     Nick
    0.25
     la
    0.25
    Activations Density 0.000%

    No Known Activations