© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44331
    Prev
    Next
    INDEX
    Explanations

    Turing Machine tape, segmented, dimensional

    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
     thighs
    0.41
     excretion
    0.39
     stupidity
    0.39
     barbarian
    0.36
    醪
    0.36
    wl
    0.35
    样
    0.35
     titt
    0.35
     shui
    0.34
     ingestion
    0.34
    POSITIVE LOGITS
     έχει
    0.40
     teclado
    0.39
    ciende
    0.38
     Unterkunft
    0.38
     эффективно
    0.37
    ৩
    0.37
    issait
    0.35
     Commentaires
    0.34
    [
    0.34
    ៣
    0.34
    Activations Density 0.004%

    No Known Activations