© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102249
    Prev
    Next
    INDEX
    Explanations

    Hopper architecture

    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
     prayed
    0.49
    ensureEqual
    0.48
    ;">
    0.48
    erode
    0.48
     సమయంలో
    0.47
     digelar
    0.46
     священ
    0.46
    サイズ
    0.46
     అయిన
    0.46
     sujetos
    0.45
    POSITIVE LOGITS
     coin
    0.54
    چ
    0.52
    itettura
    0.51
     pub
    0.51
     pot
    0.49
     heuristic
    0.49
     pratica
    0.47
     simulation
    0.47
     pamphlet
    0.47
    ars
    0.47
    Activations Density 0.000%

    No Known Activations