© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90937
    Prev
    Next
    INDEX
    Explanations

    learning styles

    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_3_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
     aneu
    0.64
     rezat
    0.63
    maximize
    0.61
    unload
    0.61
    americanos
    0.59
     skut
    0.58
    ي
    0.58
     पॉलिटी
    0.57
    ని
    0.57
     İng
    0.57
    POSITIVE LOGITS
    ك
    0.84
    ing
    0.73
     was
    0.72
    ة
    0.66
    ics
    0.62
     Voluntary
    0.61
    k
    0.60
    _{\
    0.55
    IF
    0.55
     Flexible
    0.55
    Activations Density 0.005%

    No Known Activations