© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236899
    Prev
    Next
    INDEX
    Explanations

    Muhammad's migration to Medina

    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_32_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
    嚴
    0.42
     Bypass
    0.42
    Superhero
    0.40
    STORAGE
    0.39
    Port
    0.37
     bypass
    0.37
    迁移
    0.37
     நக
    0.37
     imaging
    0.37
     柄
    0.36
    POSITIVE LOGITS
     volunt
    0.41
     contradd
    0.38
    Ꮽ
    0.38
     đau
    0.37
     pharm
    0.37
    udie
    0.36
    ନ୍
    0.36
     admirably
    0.36
     така
    0.33
    +")
    0.33
    Activations Density 0.001%

    No Known Activations