© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14917
    Prev
    Next
    INDEX
    Explanations

    Major events competitions awards

    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_13_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
    િજા
    0.57
    િર
    0.51
    🩶
    0.51
    jian
    0.51
     价
    0.50
    παϊ
    0.50
    VEY
    0.50
     ŝ
    0.50
     グレー
    0.49
     monarch
    0.49
    POSITIVE LOGITS
     It
    0.54
     möjligt
    0.54
    tn
    0.51
     If
    0.50
     qu
    0.50
    It
    0.50
     Sense
    0.50
     More
    0.49
     Marks
    0.49
     building
    0.49
    Activations Density 0.008%

    No Known Activations