© 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. 37598
    Prev
    Next
    INDEX
    Explanations

    movie script tickets clip props

    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
    يش
    0.55
    EDA
    0.54
    ACIÓN
    0.52
     Polri
    0.52
    લ
    0.52
    ualaikum
    0.52
    يته
    0.52
    ITAS
    0.49
    ي
    0.49
    ación
    0.48
    POSITIVE LOGITS
     seem
    0.57
    men
    0.51
     listeners
    0.50
     fhe
    0.50
     listener
    0.48
     arrive
    0.46
    s
    0.46
     don
    0.45
     handset
    0.45
    man
    0.45
    Activations Density 0.008%

    No Known Activations