© 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. 75951
    Prev
    Next
    INDEX
    Explanations

    payment method or gateway

    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
     khách
    0.36
     டிக்க
    0.34
    刀
    0.33
    呫
    0.33
    Subscribe
    0.32
     OO
    0.32
    стане
    0.32
    ፋ
    0.32
    OO
    0.32
    客
    0.32
    POSITIVE LOGITS
     perished
    0.35
    燦
    0.34
     Brussels
    0.33
     Gregor
    0.33
    writable
    0.33
     Beale
    0.32
     Andri
    0.32
     tapas
    0.31
     Arne
    0.31
     paisley
    0.31
    Activations Density 0.002%

    No Known Activations