© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242292
    Prev
    Next
    INDEX
    Explanations

    project goals and outcomes

    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_40_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
     অয
    0.40
    ionales
    0.40
    表現
    0.39
     ორგან
    0.38
    瀆
    0.38
    身的
    0.37
    ector
    0.36
    症状
    0.36
    origin
    0.36
    consulta
    0.36
    POSITIVE LOGITS
    amano
    0.39
    lasse
    0.39
    考虑
    0.38
     unit
    0.38
    啶
    0.38
     FS
    0.37
     schne
    0.37
    چھا
    0.36
     unidade
    0.36
     units
    0.36
    Activations Density 0.009%

    No Known Activations