© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14697
    Prev
    Next
    INDEX
    Explanations

    '

    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_15_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
    PBC
    0.29
    Honestly
    0.28
    Kre
    0.27
    HCR
    0.27
    ቐ
    0.27
    Ho
    0.27
    Grazie
    0.27
     examiner
    0.27
    ູ່
    0.27
    쐞
    0.27
    POSITIVE LOGITS
     rán
    0.31
     t
    0.31
     r
    0.30
    usta
    0.29
     rafting
    0.29
     g
    0.28
    undai
    0.28
     d
    0.28
    uste
    0.28
    aire
    0.27
    Activations Density 0.023%

    No Known Activations