© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 258637
    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
     лицом
    1.28
     tradisional
    1.27
     kerap
    1.22
    уч
    1.19
    𝙱
    1.18
    damn
    1.13
    ্তিক
    1.13
    generally
    1.12
     enfrentar
    1.12
     pernah
    1.11
    POSITIVE LOGITS
    бавить
    1.11
    ద
    1.07
    ل
    0.94
    ্লিক
    0.94
     Replication
    0.93
     replication
    0.91
     dov
    0.88
    calibur
    0.88
    ㅁ
    0.88
     candidate
    0.87
    Activations Density 0.000%

    No Known Activations