© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121901
    Prev
    Next
    INDEX
    Explanations

    Valve, barochlorometer, trumpet, roasting, CO2, improvised

    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
     গল্পের
    0.39
     ફિલ્મ
    0.37
     procedimiento
    0.36
    Dogs
    0.36
    升
    0.35
     Latte
    0.35
     disorderly
    0.35
     एल्गोरि
    0.35
    ∶
    0.35
    क्षित
    0.34
    POSITIVE LOGITS
     зада
    0.44
    Valve
    0.44
    valve
    0.43
     Valve
    0.42
     valve
    0.41
    ackBar
    0.40
     Valves
    0.38
     VALVE
    0.37
    puff
    0.37
     energetics
    0.37
    Activations Density 0.003%

    No Known Activations