© 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. 13596
    Prev
    Next
    INDEX
    Explanations

    breakdown or breaking

    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
    iaire
    0.34
    br
    0.33
    𝓖
    0.32
    itary
    0.32
    став
    0.31
     letras
    0.30
    th
    0.29
    ong
    0.29
    arias
    0.29
     dividir
    0.29
    POSITIVE LOGITS
    펨
    0.33
    >=</
    0.32
     impor
    0.32
     לך
    0.32
     booster
    0.32
    #
    0.32
     essere
    0.32
     capire
    0.31
     curtailed
    0.31
    '=
    0.31
    Activations Density 0.454%

    No Known Activations