© 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. 19052
    Prev
    Next
    INDEX
    Explanations

    split, possible, increasing, remainder, plus, with

    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
     जगदीश
    0.39
     주세요
    0.38
     Hodgson
    0.38
     imassa
    0.37
     ediyoruz
    0.37
     TRANSPORTURI
    0.37
     ቲ
    0.36
     уровня
    0.36
     न्यायालया
    0.36
     କ
    0.35
    POSITIVE LOGITS
    ↵
    0.51
    estimates
    0.38
    Measurement
    0.37
    split
    0.35
    ؤ
    0.34
    N
    0.34
    pages
    0.34
    Formation
    0.33
    andos
    0.33
    ch
    0.33
    Activations Density 0.097%

    No Known Activations