© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175625
    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_24_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
    ٹا
    0.50
     주요
    0.44
    lying
    0.44
    𝐭
    0.43
     Surveillance
    0.43
    Coronavirus
    0.42
     Tactics
    0.41
    belt
    0.41
     اقدامات
    0.41
    ▲
    0.40
    POSITIVE LOGITS
    守护
    0.43
    泉
    0.41
     powerless
    0.39
     prenatal
    0.39
     cliche
    0.38
     contented
    0.38
    ርግ
    0.38
     fright
    0.37
    RENDER
    0.37
     sacar
    0.37
    Activations Density 0.000%

    No Known Activations