© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256570
    Prev
    Next
    INDEX
    Explanations

    each [recipient/container]

    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_10_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
    untuk
    0.58
     renounce
    0.55
     untuk
    0.54
     serialize
    0.53
    Phys
    0.53
     intercourse
    0.52
    NULL
    0.52
    깅
    0.51
     loneliness
    0.51
    physiology
    0.50
    POSITIVE LOGITS
     নির্ধারিত
    0.61
     bequeathed
    0.57
     Tage
    0.54
     slated
    0.52
    aquin
    0.52
     பாஜக
    0.51
     inherited
    0.51
    前辈
    0.51
    指定的
    0.50
    ingen
    0.50
    Activations Density 0.002%

    No Known Activations