© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8762
    Prev
    Next
    INDEX
    Explanations

    <!DOCTYPE html

    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_3_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
    Н
    1.07
     gotta
    0.95
    نون
    0.92
    적인
    0.92
    a
    0.87
    Attention
    0.87
    ल
    0.86
    р
    0.84
    ট
    0.83
     vera
    0.82
    POSITIVE LOGITS
    蓣
    0.91
    ται
    0.83
    ӥ
    0.82
    wheels
    0.81
     uzav
    0.81
    CAG
    0.81
     organizacji
    0.81
    inescence
    0.80
    კი
    0.79
    ági
    0.78
    Activations Density 0.004%

    No Known Activations