© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107029
    Prev
    Next
    INDEX
    Explanations

    divine

    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_1_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
    ات
    1.32
    k
    1.10
    5
    1.09
    ल
    1.09
    ut
    1.06
    os
    1.06
    л
    1.06
    }$.
    1.05
     (
    1.02
    ты
    1.02
    POSITIVE LOGITS
     は
    1.09
     talisman
    1.07
    ᱐
    1.05
    Z
    1.01
     lifelong
    0.99
     severely
    0.97
    示す
    0.97
     police
    0.96
     hilly
    0.96
     spune
    0.95
    Activations Density 0.001%

    No Known Activations