© 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. 8043
    Prev
    Next
    INDEX
    Explanations

    case law, header, notes

    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
    берите
    0.87
    Rpc
    0.86
     pinion
    0.85
    ாம்
    0.83
    이
    0.83
     mitad
    0.82
     degrés
    0.82
     forgiven
    0.82
    ς
    0.82
     curbing
    0.81
    POSITIVE LOGITS
    ying
    0.76
    ین
    0.76
    me
    0.76
    ri
    0.75
    ный
    0.74
    ma
    0.74
    de
    0.73
    ten
    0.73
    お客
    0.72
    сть
    0.71
    Activations Density 0.009%

    No Known Activations