© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127483
    Prev
    Next
    INDEX
    Explanations

    generating sequence or collection of items

    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_37_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
    asati
    0.42
    Engl
    0.40
    䉼
    0.40
    齧
    0.38
    itya
    0.37
    看向
    0.37
    SIGNAL
    0.37
    }|^{
    0.36
    oscale
    0.36
    หลด
    0.36
    POSITIVE LOGITS
     letters
    0.56
     ABC
    0.55
     abc
    0.53
     Letters
    0.52
    字母
    0.49
     alph
    0.48
    Letters
    0.48
     alphabetically
    0.46
    ABC
    0.46
     Letter
    0.46
    Activations Density 0.006%

    No Known Activations