© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35271
    Prev
    Next
    INDEX
    Explanations

    import completion/utility/creation

    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_7_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
    "
    0.89
    د
    0.81
    ب
    0.66
    ,
    0.65
    ر
    0.64
    ي
    0.63
    ר
    0.62
    م
    0.61
    দ
    0.60
    0.58
    POSITIVE LOGITS
    с
    0.66
     ചെയ്യ
    0.64
     nostra
    0.63
    ле
    0.62
     potrebbero
    0.61
    પતિ
    0.60
     μη
    0.59
     ପ୍ର
    0.59
     посредством
    0.59
     помогают
    0.59
    Activations Density 0.001%

    No Known Activations