© 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. 257245
    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
    nya
    1.22
    ant
    1.08
    n
    1.07
    lijk
    1.06
    да
    1.04
    م
    0.99
    growth
    0.99
    theless
    0.99
    ান্য
    0.98
    married
    0.96
    POSITIVE LOGITS
    今
    1.40
     impeller
    1.29
    ﺍ
    1.26
    वे
    1.24
     amplitude
    1.24
     spins
    1.23
     develops
    1.23
     melts
    1.21
     thicken
    1.21
     circunstancias
    1.21
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.