© 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. 2929
    Prev
    Next
    INDEX
    Explanations

    permit parameter names

    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
    en
    1.16
    и
    1.05
    のは
    0.92
    ために
    0.86
    ../../
    0.82
    certification
    0.80
    pn
    0.80
    ất
    0.77
    ра
    0.77
    ened
    0.75
    POSITIVE LOGITS
     gelap
    1.20
     する
    1.20
    න්
    1.16
    ovať
    1.13
     conseguenza
    1.11
    ქვ
    1.10
     밝
    1.08
    ził
    1.06
     surgir
    1.06
     사람
    1.05
    Activations Density 0.000%

    No Known Activations