© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106182
    Prev
    Next
    INDEX
    Explanations

    Eratosthenes

    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_1_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
    i
    1.85
    ри
    1.69
    ي
    1.66
    y
    1.57
    ت
    1.49
    ল
    1.47
    n
    1.45
    ু
    1.45
    v
    1.42
    f
    1.41
    POSITIVE LOGITS
     I
    1.60
    ’
    1.21
     an
    1.16
     а
    1.13
    1.10
     і
    1.02
     إ
    1.02
     в
    1.00
     flexion
    0.99
    Name
    0.98
    Activations Density 0.001%

    No Known Activations