© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9457
    Prev
    Next
    INDEX
    Explanations

    give a sense of

    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
     getBitmap
    0.40
    xff
    0.39
    xk
    0.38
    x
    0.38
    huri
    0.36
     Dolores
    0.35
     v
    0.35
     Cortez
    0.35
     forty
    0.35
     Jai
    0.35
    POSITIVE LOGITS
     چلے
    0.42
    啰
    0.38
    辙
    0.37
    起到
    0.37
    省级
    0.36
    RIE
    0.36
    μεσα
    0.36
    chik
    0.35
    畦
    0.35
    迈
    0.35
    Activations Density 0.039%

    No Known Activations