© 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. 3159
    Prev
    Next
    INDEX
    Explanations

    freedom to / of

    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
    ্ড
    1.80
    ট
    1.61
     afectada
    1.58
     அளவிற்கு
    1.49
     basa
    1.49
    லா
    1.47
     supporting
    1.45
     koy
    1.45
     afectado
    1.44
    ใหญ่
    1.42
    POSITIVE LOGITS
    ち
    1.88
    िक
    1.81
    []);
    1.75
    家
    1.71
    operand
    1.69
    <unused391>
    1.66
    掍
    1.65
    .$\
    1.65
    ankle
    1.64
     अबा
    1.63
    Activations Density 0.012%

    No Known Activations