© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    laser cutting and stamping

    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
    arl
    0.50
     &
    0.50
     stems
    0.48
    Ar
    0.47
    LA
    0.47
     mre
    0.46
    he
    0.45
    2
    0.45
    fil
    0.45
    dbl
    0.45
    POSITIVE LOGITS
    吺
    0.54
     municipio
    0.53
     nombre
    0.50
    كرة
    0.50
    คา
    0.49
    يدة
    0.49
     именем
    0.48
     nasz
    0.48
     habido
    0.48
    Можно
    0.47
    Activations Density 0.031%

    No Known Activations