© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217312
    Prev
    Next
    INDEX
    Explanations

    the following noun

    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
    忌
    0.48
    वरिश
    0.42
     कम्युनिकेशन
    0.41
     merasa
    0.40
    liners
    0.40
    NOD
    0.40
    Benzoimidazol
    0.39
     беремен
    0.38
     अवलोकन
    0.38
    ു
    0.38
    POSITIVE LOGITS
     tons
    0.45
     prices
    0.42
     timestamp
    0.41
     mant
    0.40
     c
    0.39
     horseshoe
    0.38
     bec
    0.37
     sunflowers
    0.36
     reason
    0.36
     rc
    0.36
    Activations Density 0.000%

    No Known Activations