© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247188
    Prev
    Next
    INDEX
    Explanations

    linked list

    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_40_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
     solidaridad
    0.39
     smells
    0.38
     Smash
    0.38
    閉じ
    0.38
    fassung
    0.38
    orette
    0.38
    collage
    0.37
    ᠣ
    0.36
    foil
    0.36
    ::$
    0.36
    POSITIVE LOGITS
     পুষ
    0.38
    μέ
    0.37
     Amid
    0.35
     '}
    0.35
     फॉलो
    0.34
     потреб
    0.34
    ැනි
    0.34
     Pup
    0.34
    स्फी
    0.34
     Germ
    0.33
    Activations Density 0.000%

    No Known Activations