© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 66426
    Prev
    Next
    INDEX
    Explanations

    but

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     enough
    0.52
    enough
    0.49
     now
    0.48
    ijek
    0.40
    &&\
    0.40
     Теперь
    0.39
     теперь
    0.39
     Enough
    0.39
    sees
    0.39
     тепер
    0.38
    POSITIVE LOGITS
     Ừ
    0.40
     truths
    0.38
    iffy
    0.37
     truth
    0.37
    原始内容存档
    0.37
    Truth
    0.37
     unimplemented
    0.36
    முருக
    0.36
    роде
    0.35
     aprecia
    0.35
    Activations Density 0.006%

    No Known Activations