© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51234
    Prev
    Next
    INDEX
    Explanations

    The challenge/most/trick/danger/critical

    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
     defam
    0.44
    gham
    0.39
    日が
    0.39
     ಶ್ರೀ
    0.38
    вро
    0.38
     ibid
    0.37
     pice
    0.37
    䤃
    0.37
     jahr
    0.36
    HOBBIT
    0.36
    POSITIVE LOGITS
     importantly
    0.57
     advantage
    0.54
     benefit
    0.51
     drawback
    0.51
     important
    0.50
     irony
    0.47
    遗憾
    0.47
     trick
    0.47
     caveat
    0.46
     Vorteil
    0.46
    Activations Density 0.046%

    No Known Activations