© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245491
    Prev
    Next
    INDEX
    Explanations

    Asset menu, Coroutine, Tag

    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_40_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
    虚拟机
    0.40
     Californie
    0.38
     dx
    0.38
     books
    0.37
    opan
    0.37
     Oekra
    0.37
     Italien
    0.37
    訃
    0.37
     Fate
    0.36
     Казах
    0.36
    POSITIVE LOGITS
     పట్ట
    0.42
    సరం
    0.40
     შეიძ
    0.38
    MRC
    0.38
    Открыть
    0.38
    Ignore
    0.38
     roundup
    0.37
     nhắn
    0.37
     عش
    0.36
    Btns
    0.36
    Activations Density 0.000%

    No Known Activations