© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206106
    Prev
    Next
    INDEX
    Explanations

    language skills

    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_20_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
     keterampilan
    0.30
    skills
    0.29
     skills
    0.27
     навыки
    0.24
     аудио
    0.24
    桫
    0.24
     Skills
    0.23
    movied
    0.23
     tuyển
    0.23
     epitaxial
    0.23
    POSITIVE LOGITS
    Ser
    0.21
     slightly
    0.21
    Unit
    0.21
    e
    0.21
    Mutex
    0.20
    ce
    0.20
    mathrm
    0.20
    unit
    0.20
     bound
    0.20
    surge
    0.19
    Activations Density 0.004%

    No Known Activations