© 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
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 235323
    Prev
    Next
    INDEX
    Explanations

    water ice, volcanic

    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_32_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
     gardener
    0.34
    agy
    0.33
     brief
    0.32
     afloat
    0.32
    渦
    0.32
     lip
    0.31
     utilization
    0.31
     unified
    0.30
     গেল
    0.30
     Constraints
    0.30
    POSITIVE LOGITS
     содержи
    0.38
     JS
    0.38
     js
    0.36
     deaminase
    0.36
    在中
    0.34
    鉗
    0.34
     Express
    0.33
     अमित
    0.33
     Lucia
    0.33
    沉积
    0.33
    Activations Density 0.002%

    No Known Activations