© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125723
    Prev
    Next
    INDEX
    Explanations

    informing claims or statements

    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_37_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
     everybody
    0.46
     everyone
    0.46
    }}+\
    0.39
    everyone
    0.39
     somebody
    0.38
    Everybody
    0.37
     biggest
    0.37
     সকলে
    0.37
    大家
    0.37
    最大的
    0.37
    POSITIVE LOGITS
     nonresident
    0.37
    ABASE
    0.36
    啪
    0.36
     ครอง
    0.36
    thane
    0.35
    ucket
    0.35
    urenc
    0.35
    顧問
    0.35
     CT
    0.35
     bureau
    0.35
    Activations Density 0.000%

    No Known Activations