© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 205546
    Prev
    Next
    INDEX
    Explanations

    best / most / range / results / testing / more

    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_25_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
     cantante
    0.32
     tellement
    0.31
     capsules
    0.30
     felices
    0.29
     esforços
    0.29
     veoma
    0.29
    賣
    0.28
     caballo
    0.28
    าท
    0.28
    പാട്
    0.28
    POSITIVE LOGITS
    斻
    0.28
    Rom
    0.27
     合
    0.27
    Admin
    0.27
    Unlike
    0.27
    ЛЯ
    0.26
    ukur
    0.26
     управление
    0.26
    iyal
    0.26
    Available
    0.25
    Activations Density 0.006%

    No Known Activations