© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168257
    Prev
    Next
    INDEX
    Explanations

    organic words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     z
    2.47
     ز
    2.02
     з
    1.96
    z
    1.86
     Z
    1.50
    Z
    1.48
    ｚ
    1.47
    ز
    1.41
     ז
    1.41
    𝑧
    1.37
    POSITIVE LOGITS
     Organic
    0.37
     wacht
    0.35
     organic
    0.34
     Morr
    0.33
     Paar
    0.33
     Precip
    0.32
     Barton
    0.32
     Luk
    0.32
     Maar
    0.32
    ដល់
    0.32
    Activations Density 0.009%

    No Known Activations