© 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. 5035
    Prev
    Next
    INDEX
    Explanations

    paraphrasing

    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
    suk
    1.11
     abbreviation
    0.90
    $-
    0.88
    یر
    0.88
    ...+
    0.86
    "<
    0.85
    कि
    0.83
     نها
    0.83
    -\
    0.83
    ाइवेट
    0.82
    POSITIVE LOGITS
    ați
    1.04
    𝘦
    0.99
    NOM
    0.98
    אם
    0.92
    stücke
    0.91
     mentales
    0.90
     dislocations
    0.89
    раў
    0.89
    comers
    0.89
    𝘮
    0.88
    Activations Density 0.003%

    No Known Activations