© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176102
    Prev
    Next
    INDEX
    Explanations

    GUI element initialization

    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_20_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
     উঠছে
    0.42
    偶然
    0.42
    potential
    0.42
    )
    0.42
    time
    0.41
    how
    0.41
    PR
    0.40
    tool
    0.40
    ताप
    0.40
     using
    0.39
    POSITIVE LOGITS
    蘞
    0.46
     കൊണ്ട്
    0.46
     rappers
    0.45
     suspensions
    0.45
     conforto
    0.45
     receivables
    0.45
     steering
    0.45
     selv
    0.45
     próprio
    0.45
     rifles
    0.44
    Activations Density 0.001%

    No Known Activations