© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88417
    Prev
    Next
    INDEX
    Explanations

    list of things, ways, or suggestions

    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_23_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
    ս
    0.43
    繼續
    0.40
     بمن
    0.40
     bothering
    0.39
    indow
    0.38
    继续
    0.38
     discernment
    0.37
     clothe
    0.37
     lobe
    0.37
     bronchial
    0.37
    POSITIVE LOGITS
    佔
    0.42
     mantan
    0.41
    占
    0.40
     reacciones
    0.38
    Quando
    0.37
     занимает
    0.37
    дії
    0.36
     Calculated
    0.36
     propuestas
    0.36
     Calculations
    0.36
    Activations Density 0.020%

    No Known Activations