© 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. 51112
    Prev
    Next
    INDEX
    Explanations

    sentiment analysis and classification

    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
    льный
    0.82
    هم
    0.76
     می
    0.74
    也
    0.73
     to
    0.72
    で
    0.72
    っくり
    0.71
    が
    0.70
    ઈ
    0.70
    を
    0.70
    POSITIVE LOGITS
     bruke
    0.80
     tio
    0.77
     hvilket
    0.75
    eni
    0.70
     infile
    0.69
    nThe
    0.69
    amente
    0.68
     opera
    0.68
     sida
    0.68
     buddh
    0.68
    Activations Density 0.000%

    No Known Activations