© 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. 32413
    Prev
    Next
    INDEX
    Explanations

    describes awe

    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
    ளால்
    0.39
    лимпий
    0.36
     Woodland
    0.35
     disposable
    0.34
    鐧
    0.34
     MAT
    0.33
    mai
    0.33
    हूं
    0.33
    নো
    0.33
    ভ
    0.33
    POSITIVE LOGITS
     taking
    2.44
    Taking
    2.42
    taking
    2.41
     Taking
    2.34
     tomando
    1.66
     takers
    1.59
     taker
    1.57
    taker
    1.54
     prenant
    1.41
    tak
    1.32
    Activations Density 0.002%

    No Known Activations