© 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. 8779
    Prev
    Next
    INDEX
    Explanations

    power bi

    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
    ный
    1.18
     sopr
    1.08
    scrollView
    1.03
     recorrido
    1.02
     willen
    1.00
    ﾝ
    0.99
     inici
    0.99
    enek
    0.96
    }(
    0.96
    ড
    0.95
    POSITIVE LOGITS
    alek
    1.09
     быть
    1.05
    ካከል
    1.04
    ⟶
    1.04
    अग
    1.04
    akim
    1.04
    alyse
    1.01
    Century
    1.00
     variés
    0.99
    荑
    0.99
    Activations Density 0.003%

    No Known Activations