© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 38462
    Prev
    Next
    INDEX
    Explanations

    cinema, film, lighting, expression

    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_11_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
    os
    0.61
    Se
    0.55
    ord
    0.54
    Time
    0.54
    S
    0.52
    ass
    0.51
    P
    0.51
     Semua
    0.50
    𝗼
    0.50
    oh
    0.50
    POSITIVE LOGITS
     اظ
    0.51
     ნაკ
    0.50
    其
    0.49
     ควร
    0.48
     flotation
    0.47
     notor
    0.46
     nive
    0.46
     collega
    0.46
     airplane
    0.46
     modeller
    0.46
    Activations Density 0.033%

    No Known Activations