© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51457
    Prev
    Next
    INDEX
    Explanations

    building or division against itself

    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_30_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
    }\|\
    0.39
     innocent
    0.38
     inoc
    0.38
     drivers
    0.38
     மாதிர
    0.38
     pairings
    0.37
     cohorts
    0.36
     underdog
    0.36
     Tilt
    0.36
    opu
    0.36
    POSITIVE LOGITS
     Requested
    0.39
     Curso
    0.39
    哳
    0.38
    usele
    0.38
     abgerufen
    0.36
     Suggested
    0.35
     Middleton
    0.35
    巒
    0.35
     сначала
    0.34
     ascol
    0.34
    Activations Density 0.001%

    No Known Activations