© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45151
    Prev
    Next
    INDEX
    Explanations

    file reading, projectors, cameras, nomads, Rivera

    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
    '
    0.89
    ecture
    0.72
    t
    0.63
    antian
    0.61
     auxquelles
    0.60
    વા
    0.58
    embre
    0.57
    اوى
    0.57
    engaruhi
    0.57
    ми
    0.57
    POSITIVE LOGITS
     for
    0.68
    T
    0.66
    ส
    0.64
    0
    0.62
    夎
    0.60
    od
    0.60
    ஹ
    0.60
    สะ
    0.59
    S
    0.58
    া
    0.55
    Activations Density 0.009%

    No Known Activations