© 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
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66332
    Prev
    Next
    INDEX
    Explanations

    remains or continues

    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_41_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
    返
    0.41
     abc
    0.41
    akawa
    0.38
     нен
    0.38
     மே
    0.37
    abc
    0.37
    ര
    0.36
    是不
    0.36
    بيق
    0.36
    امه
    0.36
    POSITIVE LOGITS
     haven
    2.08
     hasn
    1.98
     havent
    1.85
     Haven
    1.80
     hadn
    1.77
    Haven
    1.77
     chưa
    1.73
    haven
    1.65
     belum
    1.64
     HAV
    1.44
    Activations Density 0.156%

    No Known Activations