© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6634
    Prev
    Next
    INDEX
    Explanations

    as it

    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
    ধ
    2.02
    ْد
    2.01
    herent
    2.00
    wicket
    1.99
    vskip
    1.99
    <0xDD>
    1.97
     Milliarden
    1.95
    ти
    1.94
    ный
    1.92
     Huh
    1.92
    POSITIVE LOGITS
    as
    2.29
    ar
    2.29
     espectáculo
    2.05
    enting
    2.04
    نې
    2.04
    样的
    2.02
    ்துற
    1.98
    د
    1.96
    꽝
    1.96
     faux
    1.94
    Activations Density 0.009%

    No Known Activations