© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245731
    Prev
    Next
    INDEX
    Explanations

    может, моменты, возможность

    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
    樁
    0.41
     Erst
    0.41
    CAPT
    0.38
     saída
    0.38
    haviours
    0.37
     드리
    0.37
     çıktı
    0.36
    extraction
    0.36
     convivial
    0.35
    sono
    0.35
    POSITIVE LOGITS
    ன்ன
    0.40
     paramilitary
    0.37
    大陆
    0.37
    ルコ
    0.37
     ताम
    0.36
    茧
    0.35
    Ic
    0.35
    的能力
    0.35
    ObjectIndex
    0.35
     заболевания
    0.35
    Activations Density 0.001%

    No Known Activations