© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86044
    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_23_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
    ған
    0.43
    శ్వ
    0.43
     Earnings
    0.41
     throne
    0.41
     charge
    0.39
    ᑦ
    0.39
    Didn
    0.38
    ισμό
    0.38
     simplex
    0.38
    儆
    0.37
    POSITIVE LOGITS
     ec
    0.40
    lom
    0.40
    iot
    0.40
     lom
    0.39
    ()->
    0.39
    堪
    0.39
     बेर
    0.38
     IOP
    0.38
    lon
    0.38
     tumult
    0.37
    Activations Density 0.000%

    No Known Activations