© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161290
    Prev
    Next
    INDEX
    Explanations

    sans-serif fonts

    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_2_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
    ’
    1.52
     on
    1.12
     at
    1.12
     Institute
    1.09
     el
    1.05
     utilisateur
    1.05
     artist
    1.02
    '
    1.02
     interface
    1.01
     advisor
    1.00
    POSITIVE LOGITS
    de
    1.34
    اسی
    1.29
    ى
    1.29
    ор
    1.25
    ها
    1.24
    ि
    1.22
    ang
    1.19
    inol
    1.19
    ای
    1.18
    that
    1.18
    Activations Density 0.001%

    No Known Activations