© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20143
    Prev
    Next
    INDEX
    Explanations

    un prefix

    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_56_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
    тором
    0.41
    టర్
    0.40
    LOCK
    0.39
    ИТ
    0.38
    锁定
    0.38
    ौला
    0.38
     ö
    0.36
     hepatocellular
    0.36
    爛
    0.35
     proinflammatory
    0.35
    POSITIVE LOGITS
    一
    0.49
    ذ
    0.41
    rem
    0.41
    ěru
    0.40
    刻
    0.39
    abo
    0.39
    ky
    0.38
    ্যক
    0.38
    再
    0.38
    very
    0.38
    Activations Density 0.009%

    No Known Activations