© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152630
    Prev
    Next
    INDEX
    Explanations

    returning objects or values

    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_23_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
    филлер
    0.46
    真
    0.45
     carbonic
    0.43
     טור
    0.41
     verdadero
    0.41
     ನಿಜ
    0.41
    チューブ
    0.40
    列
    0.40
     היה
    0.40
     answer
    0.40
    POSITIVE LOGITS
     hrane
    0.46
    യ്ക്ക
    0.43
    ᅱ
    0.41
     réduit
    0.41
    éf
    0.40
    hr
    0.39
    korzyst
    0.39
     Harb
    0.39
    yk
    0.38
    setHora
    0.38
    Activations Density 0.000%

    No Known Activations