© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8213
    Prev
    Next
    INDEX
    Explanations

    deep dive

    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_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
    candle
    2.52
    થા
    2.36
     часа
    2.26
     veniva
    2.24
    ‍♀️
    2.23
    彡
    2.22
     enlist
    2.22
     तरह
    2.21
     encarg
    2.18
     crop
    2.17
    POSITIVE LOGITS
     seated
    3.13
    ার্টমেন্ট
    3.03
    邃
    3.00
     eutectic
    2.82
    厚的
    2.69
     routed
    2.55
    у
    2.53
    slate
    2.46
    ם
    2.38
    د
    2.31
    Activations Density 0.151%

    No Known Activations