© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6128
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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_39_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
    nisse
    0.42
    −−
    0.42
     বিবে
    0.39
    紅色
    0.37
     મુખ્ય
    0.37
    ኛው
    0.36
    艷
    0.36
    ikk
    0.36
    તિહાસ
    0.36
     అతి
    0.35
    POSITIVE LOGITS
     accompanied
    0.42
    伴
    0.41
     placeholders
    0.40
     overlay
    0.39
     logro
    0.38
     lern
    0.38
     Inglis
    0.38
     alongside
    0.37
     Ler
    0.37
    Overlay
    0.36
    Activations Density 0.042%

    No Known Activations