© 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. 39539
    Prev
    Next
    INDEX
    Explanations

    code closing parenthesis

    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
    铢
    0.56
    w
    0.53
     portuguesa
    0.52
    ».
    0.51
     They
    0.47
     português
    0.47
     tinham
    0.47
    衹
    0.47
    :.
    0.46
    They
    0.46
    POSITIVE LOGITS
    ത്തിനായി
    0.56
    nih
    0.52
    ui
    0.52
    変更
    0.52
     Mih
    0.50
    നായി
    0.50
     una
    0.50
     intent
    0.50
    una
    0.50
    ковой
    0.50
    Activations Density 0.004%

    No Known Activations