© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24988
    Prev
    Next
    INDEX
    Explanations

    pairing

    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_10_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
    ),
    0.87
    times
    0.78
     )
    0.78
    )।
    0.75
    ri
    0.74
    !)
    0.73
    pe
    0.73
    tan
    0.73
    tions
    0.72
     on
    0.71
    POSITIVE LOGITS
    x
    0.71
    EN
    0.70
     типу
    0.70
     suiv
    0.68
     любое
    0.68
    何の
    0.68
     cuidados
    0.67
    জ্ঞা
    0.65
    ви
    0.65
    близи
    0.64
    Activations Density 0.012%

    No Known Activations