© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166540
    Prev
    Next
    INDEX
    Explanations

    ichimoku, palette, water, rain

    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_34_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
    Locked
    0.42
     পাহাড়
    0.41
     piedras
    0.40
    locked
    0.39
    Boulder
    0.39
     boulders
    0.39
    eserc
    0.39
    栍
    0.38
     hadden
    0.38
     couches
    0.38
    POSITIVE LOGITS
    糊
    0.41
     కలిసి
    0.39
     palate
    0.38
     pallet
    0.38
    palette
    0.37
     differentiation
    0.37
     palette
    0.37
     differentiator
    0.37
     EXEMPL
    0.37
     같이
    0.37
    Activations Density 0.001%

    No Known Activations