© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33875
    Prev
    Next
    INDEX
    Explanations

    operating equipment

    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_31_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
    pian
    0.41
    導演
    0.37
    पत्
    0.35
    getText
    0.35
    وية
    0.35
     Dawson
    0.34
     वजन
    0.34
    洊
    0.34
    روس
    0.34
     Bulgarian
    0.34
    POSITIVE LOGITS
     pumps
    0.43
     flanges
    0.42
     pump
    0.42
     boiler
    0.42
     Pumps
    0.40
     reactor
    0.38
     pilot
    0.38
     apparatus
    0.37
     patch
    0.36
     plant
    0.36
    Activations Density 0.082%

    No Known Activations