© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13934
    Prev
    Next
    INDEX
    Explanations

    form element

    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_40_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
    ཇ
    0.45
    Detector
    0.41
    Easing
    0.39
     tolerance
    0.38
    Sugar
    0.38
    tolerance
    0.38
    Tolerance
    0.37
    Christine
    0.37
    Crystal
    0.36
    Flask
    0.36
    POSITIVE LOGITS
     Scuola
    0.49
    洿
    0.46
     GROUP
    0.43
     grupa
    0.43
     gruppo
    0.43
     groupe
    0.42
     ग्रुप
    0.41
     группе
    0.41
     группу
    0.41
     impossibile
    0.41
    Activations Density 0.001%

    No Known Activations