© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32071
    Prev
    Next
    INDEX
    Explanations

    canvas context ctx

    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_40_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
    𒉿
    0.39
     комби
    0.39
    মোহন
    0.38
    Resizable
    0.37
    ᄒ
    0.37
    睺
    0.37
     killings
    0.37
    )=$
    0.37
     crossovers
    0.37
     subi
    0.36
    POSITIVE LOGITS
     seed
    0.50
    Seed
    0.49
    Seeds
    0.46
    中央
    0.45
    seed
    0.45
     seeds
    0.44
     Seed
    0.44
    seeds
    0.43
    Path
    0.43
    Central
    0.42
    Activations Density 0.009%

    No Known Activations