© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79474
    Prev
    Next
    INDEX
    Explanations

    multiple scripts and languages

    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_31_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
    OfDeath
    0.25
     Hayward
    0.23
     preparatory
    0.23
    鍔
    0.23
    𒁍
    0.23
    crose
    0.22
     nurs
    0.22
    üyada
    0.22
    ၺ
    0.22
     estando
    0.21
    POSITIVE LOGITS
     ഒരു
    0.21
     Dominica
    0.20
     semplici
    0.20
    事情
    0.20
    ുന്ന
    0.20
     φο
    0.20
     virkelig
    0.19
     অত্যন্ত
    0.19
    魃
    0.19
     spec
    0.19
    Activations Density 0.001%

    No Known Activations