© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171703
    Prev
    Next
    INDEX
    Explanations

    to fit/generate/handle/mention

    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_20_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
     कारगर
    0.29
    正規
    0.28
     lager
    0.27
     ganger
    0.27
     】,
    0.26
    吖
    0.26
     queer
    0.25
    ᱭ
    0.25
     discrim
    0.25
    स्पद
    0.25
    POSITIVE LOGITS
    </em>
    0.23
     McDon
    0.23
     clones
    0.23
     mult
    0.23
    Mc
    0.23
    ărilor
    0.22
    ‬
    0.22
     McCartney
    0.22
     exámenes
    0.22
     Mc
    0.22
    Activations Density 0.013%

    No Known Activations