© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206473
    Prev
    Next
    INDEX
    Explanations

    solving for variables

    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_25_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
    December
    0.37
    performs
    0.37
    Purch
    0.36
    munition
    0.35
    asibility
    0.35
    Ν
    0.35
    ມີ
    0.35
     singlet
    0.35
     Wage
    0.35
     cnt
    0.34
    POSITIVE LOGITS
     教育
    0.44
     unspoken
    0.40
     educa
    0.38
     겸
    0.38
     unsurprisingly
    0.36
     mengaj
    0.35
     यूपीएससी
    0.35
     unmarked
    0.35
     கல்வி
    0.35
    askell
    0.34
    Activations Density 0.001%

    No Known Activations