© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44450
    Prev
    Next
    INDEX
    Explanations

    conversion to religion

    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_13_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
    /
    0.55
     can
    0.53
    ikte
    0.53
     de
    0.51
    Al
    0.51
     lesions
    0.50
    О
    0.49
    Cl
    0.49
    ...
    0.48
     his
    0.48
    POSITIVE LOGITS
     بازی
    0.54
     gioco
    0.54
    बाईल
    0.54
    offerta
    0.52
    çam
    0.51
    Religion
    0.51
    dalam
    0.51
     seguente
    0.51
     giusta
    0.51
    jogador
    0.51
    Activations Density 0.021%

    No Known Activations