© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30952
    Prev
    Next
    INDEX
    Explanations

    internal monologue

    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_31_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
    Index
    0.44
    盖
    0.41
    "\
    0.41
     frees
    0.40
     Index
    0.40
     foreign
    0.39
     ge
    0.38
     index
    0.38
     indexes
    0.37
    蓋
    0.37
    POSITIVE LOGITS
     souls
    0.41
     ͡
    0.39
     душа
    0.39
     خلينا
    0.39
     pecados
    0.38
    我就
    0.38
     Souls
    0.38
     psico
    0.37
    ocytosis
    0.37
    ذاب
    0.37
    Activations Density 0.106%

    No Known Activations