© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36737
    Prev
    Next
    INDEX
    Explanations

    endings like quality, ling, or ous

    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_3_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
    .
    0.80
     defibr
    0.71
    。「
    0.63
     toothbrush
    0.62
     föret
    0.62
    0.61
     stere
    0.59
    。
    0.59
     maneuver
    0.58
     voltmeter
    0.58
    POSITIVE LOGITS
    ки
    0.91
    ظر
    0.79
    an
    0.78
    ми
    0.76
    at
    0.73
    ма
    0.73
    <0x80>
    0.70
    բ
    0.67
    בר
    0.65
    >:
    0.65
    Activations Density 0.009%

    No Known Activations