© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 90216
    Prev
    Next
    INDEX
    Explanations

    created

    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_60_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
     produced
    1.89
     произ
    1.73
     Produced
    1.70
    Produced
    1.62
    produced
    1.58
    产
    1.55
    産
    1.48
     produ
    1.45
    產
    1.41
     produz
    1.36
    POSITIVE LOGITS
     Created
    0.87
     created
    0.86
    created
    0.82
    Created
    0.81
     creado
    0.80
     creada
    0.78
     créée
    0.77
     criada
    0.72
     ü
    0.71
     созда
    0.68
    Activations Density 0.001%

    No Known Activations