© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43652
    Prev
    Next
    INDEX
    Explanations

    fluid buildup

    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_3_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
    CameraOpened
    0.73
     zacz
    0.63
    Y
    0.63
    AL
    0.62
    H
    0.61
    U
    0.61
    迨
    0.61
    ER
    0.59
    었
    0.59
    EN
    0.58
    POSITIVE LOGITS
     on
    1.22
    on
    0.79
     pooled
    0.70
    िंग
    0.65
     for
    0.63
    ъ
    0.62
     आंब
    0.61
    я
    0.61
    ν
    0.61
     tooling
    0.59
    Activations Density 0.001%

    No Known Activations