© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218895
    Prev
    Next
    INDEX
    Explanations

    historical events

    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_31_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
     فش
    0.35
    꾹
    0.35
     Collections
    0.35
     পুষ
    0.34
    当た
    0.34
    ButtonBar
    0.34
     physically
    0.34
     playgrounds
    0.34
     lightly
    0.34
     teclas
    0.34
    POSITIVE LOGITS
    िनियम
    0.44
     enfl
    0.40
    歎
    0.40
     rectifier
    0.40
    शक्ति
    0.39
     மகி
    0.38
     szolgált
    0.38
    鄂
    0.38
    ofil
    0.38
     trị
    0.38
    Activations Density 0.005%

    No Known Activations