© 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. 256915
    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
    pins
    1.52
    rained
    1.26
    cheng
    1.21
     flown
    1.18
     punished
    1.17
    pin
    1.16
     gunpowder
    1.15
    슨
    1.15
     practised
    1.15
    swick
    1.15
    POSITIVE LOGITS
     алге
    1.25
    ሳሪያ
    1.18
     озера
    1.16
    Dean
    1.09
    Recurs
    1.08
     FileManager
    1.08
    Whitelist
    1.06
     удобно
    1.06
     поме
    1.04
    取り
    1.04
    Activations Density 0.000%

    No Known Activations