© 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. 41061
    Prev
    Next
    INDEX
    Explanations

    abbreviations like FC, CN, CS, HTN, ICD, HFC, HFCS

    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
    لي
    0.83
    દ
    0.69
    يريا
    0.66
     herhangi
    0.64
     اي
    0.64
     أي
    0.63
     tý
    0.62
    嘏
    0.62
     skute
    0.61
    يء
    0.61
    POSITIVE LOGITS
    _
    0.85
    ts
    0.74
    heiros
    0.70
    bor
    0.68
    straction
    0.67
    ambito
    0.67
    tenir
    0.66
    s
    0.66
    heading
    0.66
    ties
    0.64
    Activations Density 0.003%

    No Known Activations