© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195950
    Prev
    Next
    INDEX
    Explanations

    privacy links

    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_27_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
    otrans
    0.34
     haste
    0.32
    oner
    0.31
    voerd
    0.31
    answer
    0.30
    closes
    0.30
    रूप
    0.30
    怵
    0.30
    pressure
    0.30
    ikle
    0.30
    POSITIVE LOGITS
     становятся
    0.33
     menjadi
    0.33
     доби
    0.31
    増や
    0.31
     এটিকে
    0.30
    にならない
    0.30
     핵심
    0.29
     upregulated
    0.29
     добиться
    0.28
     もう
    0.27
    Activations Density 0.000%

    No Known Activations