© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64879
    Prev
    Next
    INDEX
    Explanations

    slicing or thinly sliced

    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_41_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
     billy
    0.39
     keg
    0.39
    고사
    0.37
     padlock
    0.37
    \|,
    0.37
     detention
    0.36
    鸬
    0.36
     Beagle
    0.35
    க்கை
    0.35
    (\|
    0.35
    POSITIVE LOGITS
     slice
    2.33
     slices
    2.28
    slice
    2.14
     slicing
    2.11
    Slice
    2.09
     Slice
    2.09
     sliced
    2.08
    slices
    2.08
    Sliced
    1.80
    sliced
    1.80
    Activations Density 0.005%

    No Known Activations