© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207699
    Prev
    Next
    INDEX
    Explanations

    abstract thought

    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_19_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
    rophages
    0.45
    dades
    0.45
     indice
    0.44
    ന്ധി
    0.43
     dav
    0.41
    হরণ
    0.41
     sided
    0.41
    <unused10>
    0.41
     superiore
    0.41
    មើ
    0.41
    POSITIVE LOGITS
    ресень
    0.42
     беременности
    0.41
    D
    0.41
     vissza
    0.41
    ваться
    0.40
     выру
    0.40
     Advocacy
    0.40
    桔
    0.40
     основним
    0.39
     ил
    0.39
    Activations Density 0.002%

    No Known Activations