© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92150
    Prev
    Next
    INDEX
    Explanations

    risk during mistake mental toll

    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_11_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
    નની
    0.50
    bug
    0.50
    住
    0.47
    享
    0.47
    参加
    0.46
    γο
    0.46
    gré
    0.45
    hm
    0.45
    ك
    0.45
    زيز
    0.45
    POSITIVE LOGITS
     conversely
    0.56
     Α
    0.53
     oppressed
    0.52
     Parnell
    0.52
     examin
    0.52
     categorize
    0.51
     imprison
    0.51
     authorise
    0.51
     Ea
    0.51
     exudes
    0.50
    Activations Density 0.000%

    No Known Activations