© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90190
    Prev
    Next
    INDEX
    Explanations

    `calc`, `buffer`, `local`

    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_11_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
    resti
    0.60
    űr
    0.57
    ktur
    0.57
    ja
    0.55
     z
    0.52
     మీద
    0.52
    ukum
    0.52
    ät
    0.51
     य
    0.51
    kon
    0.51
    POSITIVE LOGITS
    κ
    0.55
    ｱ
    0.54
    וכ
    0.54
     contenant
    0.52
     crucifix
    0.52
     expérience
    0.52
     dynamique
    0.51
     αρκε
    0.50
    ﻛ
    0.50
    ﾎ
    0.50
    Activations Density 0.023%

    No Known Activations