© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1571
    Prev
    Next
    INDEX
    Explanations

    shortness of breath

    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
     yaw
    0.20
    unlock
    0.20
    Head
    0.19
    Unlock
    0.19
     buzz
    0.19
     awak
    0.19
     hibiscus
    0.18
    ጿ
    0.18
    peau
    0.18
    ShaderType
    0.18
    POSITIVE LOGITS
     manos
    0.21
    registr
    0.19
     inquired
    0.18
     स्टेशन
    0.18
    ăt
    0.17
     supl
    0.17
     konkurs
    0.17
    °,
    0.17
     प्रमा
    0.17
    geb
    0.17
    Activations Density 0.020%

    No Known Activations