© 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. 257423
    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
    ت
    2.19
    க
    1.26
    تهم
    1.24
    ۰۰
    1.23
    t
    1.13
    서
    1.10
    تف
    1.08
    et
    1.07
    stuffs
    1.05
    tong
    1.04
    POSITIVE LOGITS
    }//
    1.30
    iza
    1.28
     luchar
    1.23
     dobu
    1.22
     sueño
    1.21
    तात
    1.20
    После
    1.18
     idxf
    1.16
     consiglio
    1.15
     diseñado
    1.14
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.