© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60549
    Prev
    Next
    INDEX
    Explanations

    failure and success

    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_11_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
    ൈ
    0.52
    мента
    0.51
    enso
    0.51
     খোলা
    0.50
     likes
    0.50
    ся
    0.50
    ية
    0.50
     kehilangan
    0.50
    ال
    0.49
     cardinal
    0.49
    POSITIVE LOGITS
    D
    0.59
    ALS
    0.56
     Delivery
    0.56
     D
    0.56
     Money
    0.55
     Drama
    0.55
     Motor
    0.54
     Diese
    0.54
     Atau
    0.53
     Grade
    0.53
    Activations Density 0.000%

    No Known Activations