© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125625
    Prev
    Next
    INDEX
    Explanations

    chapter marker

    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_37_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
    Scheduler
    0.43
    Held
    0.41
    ണ്ടു
    0.40
    Homework
    0.38
    Outfit
    0.37
    Optimizer
    0.37
    敦
    0.36
    Fore
    0.36
    MDEw
    0.35
    〜
    0.35
    POSITIVE LOGITS
     markers
    1.56
     marker
    1.45
     Markers
    1.43
     Marker
    1.36
    Markers
    1.36
    markers
    1.35
    marker
    1.29
    Marker
    1.20
     marking
    1.10
     markings
    1.02
    Activations Density 0.001%

    No Known Activations