© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11156
    Prev
    Next
    INDEX
    Explanations

    punctuation and common words like 'that'

    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_13_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
    пси
    0.17
    𝘻
    0.17
    бро
    0.16
    மொழ
    0.16
    🧁
    0.16
    点
    0.16
    퀼
    0.16
    උ
    0.16
     ungefähr
    0.15
    蛋糕
    0.15
    POSITIVE LOGITS
    et
    0.18
    au
    0.18
    ened
    0.17
    pped
    0.16
    d
    0.16
    esta
    0.16
     director
    0.16
    ad
    0.16
    ferred
    0.16
    ak
    0.16
    Activations Density 0.176%

    No Known Activations