© 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. 5886
    Prev
    Next
    INDEX
    Explanations

    numbered lists or sections

    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
    er
    0.45
     Hava
    0.42
    которые
    0.41
    ️
    0.38
     undetermined
    0.37
    挲
    0.37
    र्गत
    0.37
     불구하고
    0.36
     городов
    0.36
    这不是
    0.36
    POSITIVE LOGITS
    на
    0.48
    ről
    0.47
    r
    0.45
     taget
    0.44
    kek
    0.43
    rī
    0.43
    fica
    0.42
     popis
    0.41
    naden
    0.41
    हदी
    0.40
    Activations Density 1.416%

    No Known Activations