© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214385
    Prev
    Next
    INDEX
    Explanations

    useful information

    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_50_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
    球面
    0.42
    洛
    0.40
     Murat
    0.38
    anski
    0.37
     Carlson
    0.37
    لوم
    0.37
     क्रीम
    0.37
    deren
    0.37
    marks
    0.36
    挠
    0.36
    POSITIVE LOGITS
     стоя
    0.64
     standing
    0.57
     Standing
    0.54
     pou
    0.50
     bổ
    0.49
    pou
    0.46
     стоят
    0.44
    Standing
    0.44
     Pou
    0.44
     شي
    0.43
    Activations Density 0.000%

    No Known Activations