© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 8322
    Prev
    Next
    INDEX
    Explanations

    project or module XML tags

    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
    ist
    1.63
    tenance
    1.52
    ことができます
    1.43
    ce
    1.40
    o
    1.35
    ually
    1.34
    blah
    1.33
    다면
    1.31
    графія
    1.31
    tema
    1.31
    POSITIVE LOGITS
    ل
    2.02
    ר
    2.01
    д
    1.83
     thePack
    1.68
     sesuai
    1.64
     Doremi
    1.57
    ти
    1.55
    ТИ
    1.53
    л
    1.50
    ε
    1.46
    Activations Density 0.001%

    No Known Activations