© 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. 259238
    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_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
    믄
    0.63
     urin
    0.53
     धातु
    0.49
     аст
    0.49
     тера
    0.48
    메이션
    0.48
     همان
    0.47
    sendKeyDown
    0.47
     τόσο
    0.46
    癃
    0.46
    POSITIVE LOGITS
    L
    0.50
    bread
    0.48
     resilience
    0.43
    straight
    0.43
    from
    0.42
    obj
    0.42
    Electric
    0.42
     himself
    0.41
    S
    0.41
    Republic
    0.40
    Activations Density 0.000%

    No Known Activations