© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 256790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
    ք
    1.20
    нің
    1.18
    ことです
    1.17
     noun
    1.15
     felled
    1.15
    bottomMargin
    1.14
     Approximate
    1.14
     hidrógeno
    1.13
    ಾರಿ
    1.12
     fim
    1.12
    POSITIVE LOGITS
    д
    1.19
     complic
    1.16
    т
    1.10
    тус
    1.08
    dale
    1.07
     ren
    1.07
    bruk
    1.07
    cene
    1.06
     baza
    1.05
    ્સ
    1.04
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.