© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5731
    Prev
    Next
    INDEX
    Explanations

    However,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    اب
    2.33
    pulsewidth
    2.17
     promptly
    2.11
    व
    2.07
    स
    2.07
     lepton
    2.05
    ح
    2.05
    াল
    2.02
     Poh
    2.01
    cstdlib
    1.98
    POSITIVE LOGITS
    termilk
    2.45
    tered
    2.45
    しかし
    2.39
     digress
    2.36
    ların
    2.28
     néanmoins
    2.14
    ternut
    2.13
    thole
    2.12
    ک
    1.99
    ters
    1.93
    Activations Density 0.038%

    No Known Activations