© 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-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3059
    Prev
    Next
    INDEX
    Explanations

    Biltmore Estate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    три
    2.18
    ног
    1.84
    𝟏
    1.78
    𝑰
    1.76
    𝟐
    1.74
    ció
    1.73
     qualify
    1.73
    情感
    1.69
    imageView
    1.64
    LCM
    1.62
    POSITIVE LOGITS
    د
    2.40
    т
    2.27
    н
    2.10
    л
    1.80
    ्रय
    1.78
    ﻪ
    1.77
    tedir
    1.73
    ই
    1.73
    ন
    1.72
     prerog
    1.71
    Activations Density 0.000%

    No Known Activations