© 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. 257542
    Prev
    Next
    INDEX
    Explanations

    what are the key

    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
     koa
    0.69
    äß
    0.69
     dais
    0.68
    頒
    0.68
    ële
    0.66
    oleh
    0.65
    خيص
    0.65
    emd
    0.65
    daftar
    0.65
    aturen
    0.65
    POSITIVE LOGITS
     इम्मेडिएटली
    0.75
    로는
    0.75
    AndPassword
    0.74
    사와
    0.70
     שהוא
    0.69
     vorbei
    0.66
     আর
    0.65
    ብ
    0.63
     然后
    0.63
    然后
    0.62
    Activations Density 0.000%

    No Known Activations