© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100299
    Prev
    Next
    INDEX
    Explanations

    staff

    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_14_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
     dictatorship
    0.23
     prohibits
    0.21
    ｢
    0.21
     imposes
    0.21
     ला
    0.21
     Reinhold
    0.20
     NAP
    0.20
     तानाशाह
    0.20
    ۔
    0.20
     instrument
    0.20
    POSITIVE LOGITS
    V
    0.22
     slimy
    0.22
    B
    0.22
    ô
    0.22
    崴
    0.21
    Ve
    0.21
    el
    0.21
    ie
    0.21
    X
    0.21
     ję
    0.21
    Activations Density 0.002%

    No Known Activations