© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5964
    Prev
    Next
    INDEX
    Explanations

    question prompts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    AI
    0.35
    initely
    0.33
     AI
    0.33
    ible
    0.32
     bit
    0.32
     “
    0.32
    forge
    0.32
    ly
    0.32
    her
    0.32
     isn
    0.32
    POSITIVE LOGITS
    టువంటి
    0.46
     kesalahan
    0.39
     desider
    0.38
     ഇമാം
    0.38
    銠
    0.38
    告訴
    0.38
     scrivere
    0.38
    ídas
    0.37
    孭
    0.37
     desempenho
    0.37
    Activations Density 0.009%

    No Known Activations