© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205746
    Prev
    Next
    INDEX
    Explanations

    every [noun that signifies a process or event]

    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_6_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
    I
    1.06
    ра
    1.02
    at
    0.96
    το
    0.95
    ل
    0.93
    ты
    0.92
    te
    0.90
    es
    0.90
    larda
    0.90
    К
    0.89
    POSITIVE LOGITS
    .
    0.87
    नी
    0.79
    ם
    0.75
     priest
    0.74
    ן
    0.74
    是
    0.74
    ీ
    0.73
     recombination
    0.72
    ราม
    0.71
    ני
    0.69
    Activations Density 0.002%

    No Known Activations