© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229298
    Prev
    Next
    INDEX
    Explanations

    untapped potential

    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
    ž
    1.01
    š
    0.93
    č
    0.86
     spread
    0.79
     simul
    0.75
     sailboat
    0.75
    σης
    0.74
     synthes
    0.73
    ระหว่าง
    0.73
     série
    0.71
    POSITIVE LOGITS
    p
    1.19
    kadang
    1.10
     апре
    1.07
    al
    1.05
     =
    1.03
    ak
    1.01
     ພວກເຮົາ
    1.01
     avaient
    1.00
    k
    0.99
     inclinations
    0.98
    Activations Density 0.005%

    No Known Activations