© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 4350
    Prev
    Next
    INDEX
    Explanations

    code explanations

    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
    Rep
    0.37
     string
    0.35
    ሚ
    0.35
    string
    0.33
     Rep
    0.31
     Series
    0.31
    不足
    0.30
    듭
    0.30
    점이
    0.30
     серии
    0.30
    POSITIVE LOGITS
    ົບ
    0.38
    ະພັນ
    0.36
     perintah
    0.35
     ecuaciones
    0.35
     hymns
    0.35
     جیس
    0.34
     hound
    0.34
     organiques
    0.33
    }$.,
    0.33
     gahet
    0.32
    Activations Density 0.007%

    No Known Activations