© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120321
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

    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_27_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
    тоо
    0.23
    oh
    0.22
    mund
    0.22
    au
    0.22
    und
    0.22
    ҝ
    0.21
    amond
    0.21
     piu
    0.21
    am
    0.21
    chal
    0.21
    POSITIVE LOGITS
     lepší
    0.25
     özellikleri
    0.24
    Polling
    0.24
     signification
    0.24
     ಹೊಸ
    0.24
    Polygon
    0.24
    ଞ
    0.24
     visc
    0.24
     concurs
    0.23
     сприя
    0.23
    Activations Density 0.032%

    No Known Activations