© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209843
    Prev
    Next
    INDEX
    Explanations

    Spring framework and its modules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    ামুটি
    0.41
    OTROS
    0.41
    制
    0.37
    牵
    0.37
    िकुलर
    0.37
    制品
    0.37
     эл
    0.37
    స్తున్నారు
    0.36
     привести
    0.36
    膺
    0.36
    POSITIVE LOGITS
    lette
    0.47
    rium
    0.46
    km
    0.46
    zy
    0.46
    genes
    0.44
    ėd
    0.44
    cy
    0.43
    gever
    0.43
    not
    0.43
    ogast
    0.43
    Activations Density 0.001%

    No Known Activations