© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 217559
    Prev
    Next
    INDEX
    Explanations

    package.json metadata and dependencies

    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_31_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
    DSM
    0.38
     січня
    0.38
    Cot
    0.38
     Ə
    0.38
    萬元
    0.37
    ရား
    0.37
     ڈالر
    0.37
     gdf
    0.36
     leptonic
    0.36
     beb
    0.36
    POSITIVE LOGITS
    contacts
    0.40
    contact
    0.38
     Lies
    0.37
    闰
    0.37
    რა
    0.37
     leçon
    0.36
     워
    0.36
     연락
    0.36
     Contacts
    0.36
    莘
    0.35
    Activations Density 0.002%

    No Known Activations