© 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. 116791
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     addressing
    0.56
    Ꮲ
    0.53
    ه
    0.49
    Intro
    0.49
     interprets
    0.47
     instrumentation
    0.46
     graphs
    0.45
    a
    0.45
     oppression
    0.45
     reflects
    0.45
    POSITIVE LOGITS
     المل
    0.53
     इनमें
    0.52
     río
    0.52
    ênh
    0.51
    锞
    0.51
    orgement
    0.50
     Chiến
    0.49
    怅
    0.49
     клиен
    0.49
     ehemaligen
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.