© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 260730
    Prev
    Next
    INDEX
    Explanations

    code building (`cpp`, `cmake`) and Python (`py`)

    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_5_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
    ين
    1.21
    D
    1.12
     a
    1.09
    G
    1.08
    تر
    1.03
    ב
    1.03
    č
    1.02
    m
    0.96
    ม
    0.94
    л
    0.91
    POSITIVE LOGITS
    می
    1.05
    ри
    1.04
    ות
    1.02
    ༦
    0.98
    多い
    0.97
    ի
    0.91
    них
    0.88
    った
    0.86
    னர்
    0.86
    unan
    0.86
    Activations Density 0.002%

    No Known Activations