© 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. 12550
    Prev
    Next
    INDEX
    Explanations

    English as a second language

    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
    is
    0.12
     is
    0.12
     annat
    0.12
    સે
    0.11
    uis
    0.11
     Railway
    0.11
    ou
    0.10
     س
    0.10
     د
    0.10
    oun
    0.10
    POSITIVE LOGITS
     cumbersome
    0.12
     prolonged
    0.11
     terrific
    0.11
     provoking
    0.11
     fabulous
    0.10
    畞
    0.10
     truthful
    0.10
     horrible
    0.10
     fantastic
    0.10
     wonderful
    0.10
    Activations Density 0.002%

    No Known Activations