© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2782
    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_2_width_16k_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
    ਰ
    2.75
    ない
    2.68
    !='')
    2.64
     هنگ
    2.55
    jenigen
    2.54
    ר
    2.49
    ἱ
    2.45
    ਼
    2.45
    ि
    2.44
    uire
    2.39
    POSITIVE LOGITS
    ম
    3.22
    ো
    2.66
    বসাইট
    2.40
    ene
    2.34
     waktu
    2.27
     مخطط
    2.26
    та
    2.25
     बेव
    2.25
    ्यास
    2.23
     amper
    2.23
    Activations Density 0.040%

    No Known Activations