© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140223
    Prev
    Next
    INDEX
    Explanations

    DreamWorks Animation movies

    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_12_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
     نتكلم
    0.39
    ė
    0.39
    í
    0.38
    합니다
    0.37
    owało
    0.37
     manifesting
    0.37
    लीवुड
    0.37
    ப்பாடு
    0.36
     internazionali
    0.36
    oulders
    0.36
    POSITIVE LOGITS
     الكم
    0.37
     [(
    0.37
    Aspect
    0.37
     AsRef
    0.36
     Aspects
    0.36
     Stephen
    0.36
     bus
    0.36
     Agregar
    0.36
    )})
    0.35
     Stephens
    0.35
    Activations Density 0.000%

    No Known Activations