© 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. 3442
    Prev
    Next
    INDEX
    Explanations

    dependency declarations

    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
    ist
    0.85
    est
    0.82
    er
    0.75
    ہ
    0.72
    र
    0.71
    ার
    0.69
    ڑک
    0.66
    ौड़
    0.65
    s
    0.64
    ner
    0.64
    POSITIVE LOGITS
     제거
    0.96
     importantly
    0.96
     precursors
    0.95
     étroit
    0.93
     Improper
    0.90
     insbesondere
    0.90
    mtr
    0.87
     effectu
    0.85
    র্শ
    0.84
     garlands
    0.83
    Activations Density 0.006%

    No Known Activations