© 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. 49908
    Prev
    Next
    INDEX
    Explanations

    Blandford, Force Red

    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
    ین
    0.18
    ون
    0.18
    ir
    0.18
     პ
    0.18
    as
    0.17
    یل
    0.17
    应用的
    0.16
     با
    0.16
     inactivació
    0.16
    ificar
    0.16
    POSITIVE LOGITS
    arı
    0.17
    ){
    0.17
    дите
    0.16
    )
    0.16
    )/
    0.16
    tı
    0.16
    ﺘ
    0.16
    ti
    0.15
    тери
    0.15
    )"
    0.15
    Activations Density 0.001%

    No Known Activations