© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8335
    Prev
    Next
    INDEX
    Explanations

    open-ended, open-minded, open-air

    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
    h
    2.71
    َى
    2.13
     þe
    2.12
     iste
    2.10
     pissed
    2.00
    um
    1.98
    Z
    1.96
    hah
    1.95
    ul
    1.95
    fulness
    1.90
    POSITIVE LOGITS
     questioning
    2.37
    ounced
    2.37
    彠
    2.37
    踞
    2.35
    од
    2.30
     expedient
    2.28
    ased
    2.23
    ϳ
    2.16
     ترین
    2.14
     인해
    2.13
    Activations Density 0.012%

    No Known Activations