© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 194997
    Prev
    Next
    INDEX
    Explanations

    instantiate objects

    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_15_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
    ायचे
    0.59
     ponto
    0.49
    D
    0.48
    ены
    0.47
     meyd
    0.47
     Thiết
    0.47
     Unters
    0.45
     endereço
    0.45
    G
    0.45
     तक
    0.45
    POSITIVE LOGITS
    ጨማሪ
    0.52
    䘚
    0.51
    สามารถ
    0.50
    ellation
    0.49
     decolor
    0.48
    roa
    0.46
     Hutchinson
    0.46
    iation
    0.46
     Nixon
    0.46
     DuPont
    0.46
    Activations Density 0.000%

    No Known Activations