© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88902
    Prev
    Next
    INDEX
    Explanations

    Commas

    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
     Mas
    0.73
     but
    0.65
    Mas
    0.64
     y
    0.58
     But
    0.57
    but
    0.57
     MAS
    0.52
    But
    0.48
     taking
    0.47
    mas
    0.47
    POSITIVE LOGITS
    :
    0.57
    many
    0.53
     بسیاری
    0.50
     muchos
    0.50
     muchas
    0.49
     muitas
    0.48
     muitos
    0.47
     многие
    0.47
    Many
    0.47
     molti
    0.46
    Activations Density 0.001%

    No Known Activations