© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34899
    Prev
    Next
    INDEX
    Explanations

    mechanism of action

    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_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
    i
    0.91
    as
    0.77
    this
    0.73
    uero
    0.71
    an
    0.70
    they
    0.69
    en
    0.68
    arze
    0.68
    uose
    0.67
    anel
    0.67
    POSITIVE LOGITS
     on
    0.85
     is
    0.84
    یس
    0.79
    ด
    0.76
    یک
    0.74
    ติ
    0.70
    OS
    0.70
    ре
    0.68
    く
    0.68
     It
    0.68
    Activations Density 0.001%

    No Known Activations