© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32399
    Prev
    Next
    INDEX
    Explanations

    **En resumen:**

    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_31_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
     Á
    0.39
     GROWTH
    0.38
     verbeter
    0.37
     monotonic
    0.37
     oreille
    0.36
     aerobic
    0.35
     RIVER
    0.35
     telescopic
    0.35
    setRoot
    0.35
     vez
    0.35
    POSITIVE LOGITS
    hound
    0.41
    gcf
    0.40
    '=>
    0.38
    <?=
    0.38
     начина
    0.38
    ossing
    0.37
    Craig
    0.37
    And
    0.37
     genc
    0.37
    iamine
    0.36
    Activations Density 0.005%

    No Known Activations