© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34466
    Prev
    Next
    INDEX
    Explanations

    following a phrase introducing a topic

    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_31_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
    '_
    0.34
    Ane
    0.34
    similarity
    0.33
    这两个
    0.32
     significativas
    0.32
    ῶν
    0.32
    ̔
    0.32
    歳
    0.32
    Pict
    0.32
     Similarity
    0.32
    POSITIVE LOGITS
     formed
    0.39
     formé
    0.37
     named
    0.37
     Lebanon
    0.36
     bernama
    0.36
    arında
    0.36
     irgendwo
    0.36
     edged
    0.36
     Namibia
    0.35
     Bolivia
    0.35
    Activations Density 0.043%

    No Known Activations