© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195333
    Prev
    Next
    INDEX
    Explanations

    say "-"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    iselt
    0.38
    另
    0.36
     grun
    0.35
     rootCmd
    0.32
    जिये
    0.32
     KEYUP
    0.32
     kiuj
    0.32
    \"",
    0.32
    뀌
    0.32
    ፆ
    0.32
    POSITIVE LOGITS
    –
    1.52
    −
    1.09
    ‒
    1.07
    
    1.01
    ־
    0.92
    -
    0.90
    -‘
    0.89
    ->
    0.82
    ‑
    0.80
    -'
    0.79
    Activations Density 0.009%

    No Known Activations