© 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. 6342
    Prev
    Next
    INDEX
    Explanations

    keyword class

    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
    ي
    2.72
    л
    2.42
    i
    2.35
    ी
    2.29
    iin
    2.10
    ుడు
    2.07
    ברת
    2.04
    ം
    2.02
    ुम
    2.02
    ु
    2.02
    POSITIVE LOGITS
     eigenvalue
    2.53
     redshifts
    2.33
    大脑
    2.33
     tunes
    2.29
    الد
    2.27
     wavefront
    2.21
     loudly
    2.19
    था
    2.12
     eigenvector
    2.11
     emissions
    2.09
    Activations Density 0.000%

    No Known Activations