© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4755
    Prev
    Next
    INDEX
    Explanations

    $\mathbb{R}$ or $\mathbb{Q}$

    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
    된
    0.56
    arse
    0.56
     связана
    0.53
    Հ
    0.53
    ங்கிணை
    0.52
    ercase
    0.52
     confounding
    0.52
    थन
    0.51
    bym
    0.51
    eenth
    0.51
    POSITIVE LOGITS
    л
    0.66
     GestureDetector
    0.63
     laut
    0.62
    chied
    0.61
     dissipative
    0.61
    ্যার
    0.59
    fprintf
    0.58
     стой
    0.58
    ди
    0.58
     Thrones
    0.57
    Activations Density 0.002%

    No Known Activations