© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83103
    Prev
    Next
    INDEX
    Explanations

    pivot table code

    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_0_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
    ing
    2.11
     in
    1.80
    ed
    1.59
    ة
    1.58
    ig
    1.56
    us
    1.51
    al
    1.48
    inth
    1.48
    f
    1.45
    y
    1.33
    POSITIVE LOGITS
    م
    1.49
    سی
    1.40
    اری
    1.37
    𝒄
    1.37
    3
    1.34
    ER
    1.33
    to
    1.31
    де
    1.31
     segu
    1.30
    UR
    1.29
    Activations Density 0.002%

    No Known Activations