© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221617
    Prev
    Next
    INDEX
    Explanations

    scale well, scale better

    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_10_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
    ict
    0.30
    emes
    0.27
    rod
    0.26
    I
    0.26
     THC
    0.25
    4
    0.25
    ure
    0.25
    ican
    0.24
    atured
    0.24
    heure
    0.24
    POSITIVE LOGITS
     द
    0.26
     역
    0.23
     आयात
    0.23
    വസ
    0.23
    १
    0.23
     혁
    0.23
     lackluster
    0.23
     exportation
    0.23
    of
    0.23
    בי
    0.22
    Activations Density 0.009%

    No Known Activations