© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129993
    Prev
    Next
    INDEX
    Explanations

    Khalid, Khalil, Khalifa

    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_6_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
    arı
    1.07
    la
    0.98
    daki
    0.96
    ljiv
    0.96
    ib
    0.92
    lier
    0.92
    _
    0.92
     את
    0.91
    are
    0.89
    lilik
    0.89
    POSITIVE LOGITS
    </h3>
    1.08
     It
    1.06
    ே
    1.03
    αν
    1.02
    ار
    0.96
    سل
    0.95
    м
    0.91
    ха
    0.89
    ות
    0.89
    ند
    0.88
    Activations Density 0.000%

    No Known Activations