© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 142551
    Prev
    Next
    INDEX
    Explanations

    IELTS writing and speaking

    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_0_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
     I
    1.37
    G
    1.36
     IUCN
    1.35
    할
    1.35
     Í
    1.34
    み
    1.34
     Į
    1.33
    어졌
    1.31
    在
    1.31
     NSURL
    1.30
    POSITIVE LOGITS
    as
    1.83
     can
    1.67
    el
    1.61
    on
    1.52
    ca
    1.52
    p
    1.49
    od
    1.46
     are
    1.45
    ger
    1.45
    at
    1.45
    Activations Density 0.001%

    No Known Activations