© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99424
    Prev
    Next
    INDEX
    Explanations

    story of

    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_16_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
     मिळाले
    0.52
    מר
    0.52
    間違い
    0.49
     ውስጥ
    0.48
    間違
    0.48
    மலை
    0.47
    ಪ್ಪು
    0.47
    달
    0.45
    بح
    0.45
    お子
    0.45
    POSITIVE LOGITS
     simult
    0.48
     subjug
    0.47
     absor
    0.47
     compartmental
    0.45
     fate
    0.44
     следу
    0.44
     cellular
    0.44
     pers
    0.43
    .
    0.43
     lact
    0.43
    Activations Density 0.000%

    No Known Activations