© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234114
    Prev
    Next
    INDEX
    Explanations

    book titles

    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
     kur
    0.42
    訸
    0.41
    kur
    0.40
    Kur
    0.38
     config
    0.38
     Kur
    0.38
    ellt
    0.37
    Evaluate
    0.37
    Kurt
    0.37
     Evaluate
    0.36
    POSITIVE LOGITS
    YP
    0.43
    ᄍ
    0.43
    ৃঙ্খলা
    0.40
     الفيز
    0.39
    𝕦
    0.39
     bends
    0.39
    ल्टी
    0.38
     enjoin
    0.38
     பஞ்ச
    0.38
    apprentissage
    0.38
    Activations Density 0.000%

    No Known Activations