© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 238241
    Prev
    Next
    INDEX
    Explanations

    it does/can/onto

    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_25_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
     мі
    0.40
    สิ่ง
    0.37
     الدهون
    0.37
     squeeze
    0.36
     Meaning
    0.35
     комп
    0.35
     적
    0.35
    Sums
    0.35
     pch
    0.35
     meu
    0.34
    POSITIVE LOGITS
    elve
    0.38
     deploying
    0.38
    thiophene
    0.36
    ఝ
    0.36
     entrances
    0.35
     zoning
    0.35
     wealthiest
    0.34
    ークル
    0.34
    ારા
    0.34
    吭
    0.33
    Activations Density 0.025%

    No Known Activations