© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158482
    Prev
    Next
    INDEX
    Explanations

    &

    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
    ブリッド
    0.42
     LIN
    0.41
     Stellar
    0.39
     profondes
    0.39
     प्रसार
    0.39
    Lincoln
    0.39
     penjelasan
    0.38
    怛
    0.38
    oksi
    0.37
     Lincoln
    0.36
    POSITIVE LOGITS
     Foy
    0.43
     Adresse
    0.43
     curling
    0.43
    rein
    0.42
    resting
    0.40
     Coyote
    0.40
    rim
    0.40
    qing
    0.39
    დომ
    0.39
    青
    0.38
    Activations Density 0.006%

    No Known Activations