© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 198166
    Prev
    Next
    INDEX
    Explanations

    exponents

    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_9_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
    atory
    0.49
    nate
    0.49
    大量
    0.48
    ತ್ರೆ
    0.48
     one
    0.48
    etor
    0.46
    ᱘
    0.46
    cuno
    0.46
    L
    0.46
     گاڑی
    0.46
    POSITIVE LOGITS
     ensembles
    0.49
    ับ
    0.49
    ibilities
    0.48
     logins
    0.48
     dataGenerator
    0.48
     transplants
    0.47
    )...
    0.47
     warnings
    0.47
     blossoms
    0.47
     extremists
    0.47
    Activations Density 0.000%

    No Known Activations