© 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. 10616
    Prev
    Next
    INDEX
    Explanations

    House of Orange

    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
    ゞ
    0.39
    Brain
    0.38
    Bra
    0.37
     बहनों
    0.37
    CHA
    0.36
    typicode
    0.36
    డా
    0.36
    PanelVisual
    0.36
    Lus
    0.36
     Prav
    0.35
    POSITIVE LOGITS
     δ
    0.38
     bef
    0.38
     Regent
    0.36
     Arrow
    0.36
    接
    0.36
     canaux
    0.35
    ℍ
    0.35
     Belf
    0.35
     placer
    0.35
     বাজ
    0.34
    Activations Density 0.032%

    No Known Activations