© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18031
    Prev
    Next
    INDEX
    Explanations

    CH

    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_15_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
     Möbel
    0.48
     również
    0.43
    ί
    0.43
     abdominal
    0.43
    傘
    0.42
     Mortgage
    0.42
     around
    0.40
    ления
    0.40
    También
    0.40
    始め
    0.39
    POSITIVE LOGITS
     painter
    0.44
     tinham
    0.44
     كانت
    0.42
     splic
    0.39
     scenic
    0.39
    ๙
    0.39
    :'
    0.38
     เอ
    0.38
    SizeBytes
    0.38
     triplicate
    0.38
    Activations Density 0.057%

    No Known Activations