© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11351
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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_13_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
     Reid
    0.45
     Introdu
    0.44
     Reduction
    0.42
    یف
    0.42
     Harden
    0.41
    喜
    0.41
     Diagn
    0.40
     Джа
    0.40
     Reduces
    0.40
     હતો
    0.40
    POSITIVE LOGITS
     vertigo
    0.52
     vetro
    0.49
    ল
    0.48
     unfavourable
    0.47
     glassy
    0.47
     w
    0.46
     obey
    0.46
     underground
    0.46
     стекла
    0.45
     instabilities
    0.44
    Activations Density 0.097%

    No Known Activations