© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260611
    Prev
    Next
    INDEX
    Explanations

    manage project

    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_22_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
     flatter
    0.45
    ന്മാ
    0.41
     act
    0.39
     develop
    0.38
     des
    0.38
     imagine
    0.38
     insightful
    0.37
    我
    0.37
     odd
    0.37
     feel
    0.36
    POSITIVE LOGITS
    évén
    0.43
    ovember
    0.40
    avanja
    0.38
    avanje
    0.37
    ্ভ
    0.37
    ouv
    0.36
    ęcie
    0.36
     인증
    0.36
     የግ
    0.36
    geving
    0.35
    Activations Density 0.002%

    No Known Activations