© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227347
    Prev
    Next
    INDEX
    Explanations

    Owl City | adores | ors

    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_6_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
    1.04
     bathtub
    0.80
     $$\
    0.80
     pross
    0.78
     parlor
    0.77
    EK
    0.77
    Theater
    0.75
     Year
    0.74
     wrestle
    0.74
     dispatcher
    0.74
    POSITIVE LOGITS
    ي
    2.06
    י
    1.66
    ש
    1.55
    л
    1.54
    та
    1.40
    س
    1.40
    ش
    1.38
    σ
    1.29
    ι
    1.24
    ک
    1.23
    Activations Density 0.000%

    No Known Activations