© 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. 4822
    Prev
    Next
    INDEX
    Explanations

    work to mitigate

    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
     endonuclease
    2.39
     skimage
    2.19
     dearest
    2.18
    с
    2.16
     đón
    2.14
     presumed
    2.09
     foreclose
    2.09
     Opus
    2.07
     altogether
    2.05
    מ
    2.04
    POSITIVE LOGITS
    ת
    2.11
    asında
    2.08
    ively
    2.06
    𝘪
    2.03
    ingly
    1.99
    ″]
    1.95
    ofen
    1.93
    am
    1.92
     ropes
    1.92
     hairs
    1.89
    Activations Density 0.030%

    No Known Activations