© 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. 8572
    Prev
    Next
    INDEX
    Explanations

    tell me:

    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
    ت
    2.02
    ת
    1.92
    estructive
    1.80
    ة
    1.76
    ात
    1.74
    ed
    1.69
    нд
    1.65
    ibernate
    1.64
    ️
    1.63
     Damit
    1.59
    POSITIVE LOGITS
    м
    1.78
    ll
    1.69
    不是
    1.58
    مة
    1.51
     μέσω
    1.50
    textup
    1.50
    ن
    1.49
    ーション
    1.47
    ibbean
    1.47
     реша
    1.46
    Activations Density 0.013%

    No Known Activations