© 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. 16321
    Prev
    Next
    INDEX
    Explanations

    legroom or light wash

    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
     beings
    0.41
     duel
    0.35
     atmosphere
    0.35
    هُ
    0.35
    媒
    0.35
    닷
    0.35
    <unused51>
    0.34
    ()))
    0.34
    ukebox
    0.34
    Atm
    0.34
    POSITIVE LOGITS
    వా
    0.44
    ༣
    0.43
     waist
    0.42
     వా
    0.40
     Kunde
    0.39
     منٹو
    0.39
     Waist
    0.39
    謖
    0.38
    ്യാ
    0.37
     FAILURE
    0.37
    Activations Density 0.015%

    No Known Activations