© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43281
    Prev
    Next
    INDEX
    Explanations

    .NET CLI and SDK

    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_22_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
     _
    0.60
    Q
    0.50
     >
    0.48
     Q
    0.47
    内部
    0.46
     Angles
    0.44
     Z
    0.44
     Ks
    0.44
     Spaces
    0.43
     Vitamin
    0.43
    POSITIVE LOGITS
    тем
    0.44
    önig
    0.43
    ílio
    0.41
    ökk
    0.41
     resTmp
    0.41
     assistência
    0.41
     tecnologie
    0.40
     మాత్ర
    0.40
     окт
    0.40
    ênio
    0.40
    Activations Density 0.002%

    No Known Activations