© 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. 7969
    Prev
    Next
    INDEX
    Explanations

    internal combustion engine

    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
    ríklad
    1.45
    ură
    1.40
    ાળ
    1.30
    િંગ
    1.30
     És
    1.28
     underlies
    1.26
     $:
    1.26
    fono
    1.25
    viation
    1.25
    ดี๋ยว
    1.24
    POSITIVE LOGITS
     والخ
    1.68
    讧
    1.57
     Lle
    1.56
     automorphisms
    1.56
    exams
    1.53
     aire
    1.47
     internos
    1.45
     automorphism
    1.45
    ক
    1.43
     olefins
    1.43
    Activations Density 0.051%

    No Known Activations