© 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. 176088
    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_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
    Dec
    0.47
    žev
    0.40
    ।)
    0.39
    қ
    0.39
    Do
    0.39
     oynuyoruz
    0.39
    en
    0.38
    、
    0.38
    <0x0D>
    0.38
    延长
    0.38
    POSITIVE LOGITS
     สุด
    0.54
     snaps
    0.50
     inn
    0.49
     Supplied
    0.46
     сооб
    0.45
     titanium
    0.45
     ihrem
    0.44
     datasource
    0.44
     uploaded
    0.44
     их
    0.44
    Activations Density 0.000%

    No Known Activations