© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7723
    Prev
    Next
    INDEX
    Explanations

    template matching, self-similar

    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_40_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
     heavy
    0.42
    atzeko
    0.41
     zákaz
    0.38
     assessors
    0.37
    キロ
    0.36
     hybridized
    0.36
    ʒ
    0.36
     semn
    0.36
     Соб
    0.35
     Cæ
    0.35
    POSITIVE LOGITS
    Disc
    0.37
     precedent
    0.37
    梯
    0.37
    Polish
    0.36
    Markers
    0.36
    DEVICE
    0.36
     बांग
    0.35
    Housing
    0.35
     खोला
    0.35
     धैर्य
    0.35
    Activations Density 0.016%

    No Known Activations