© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133782
    Prev
    Next
    INDEX
    Explanations

    Vikunya language fragments

    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_1_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
     in
    1.55
     l
    1.11
    ă
    1.09
    izing
    1.09
    า
    1.08
    я
    1.06
     forensics
    1.05
    ë
    1.05
     pancake
    1.04
    ர்
    1.03
    POSITIVE LOGITS
    al
    1.37
    dokument
    1.34
    dx
    1.29
    ।
    1.29
    tn
    1.26
    diendo
    1.23
    d
    1.21
    ކ
    1.20
    dan
    1.20
    cf
    1.18
    Activations Density 0.000%

    No Known Activations