© 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. 218259
    Prev
    Next
    INDEX
    Explanations

    filter, ForAll, Callable

    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
    ge
    0.55
     second
    0.54
     Koh
    0.54
     v
    0.52
     ff
    0.52
     hati
    0.52
     היה
    0.51
     i
    0.50
    ase
    0.50
     wasser
    0.50
    POSITIVE LOGITS
    нт
    0.53
    никам
    0.53
    том
    0.52
    ал
    0.52
    тап
    0.52
    ට්
    0.51
    вест
    0.51
    ногие
    0.51
    برای
    0.49
    ిత
    0.48
    Activations Density 0.000%

    No Known Activations