© 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. 17453
    Prev
    Next
    INDEX
    Explanations

    redstone

    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
     FRAN
    0.40
     Sticker
    0.38
    Snap
    0.38
    istor
    0.36
     Snap
    0.36
    Entities
    0.35
    avut
    0.35
    识
    0.35
     SNAP
    0.34
    Training
    0.34
    POSITIVE LOGITS
     metadata
    0.45
    ترض
    0.43
     minerals
    0.38
     shang
    0.38
     dioxide
    0.37
    Nickname
    0.37
     escalate
    0.37
    ␊
    0.37
    둴
    0.37
     सिल
    0.36
    Activations Density 0.002%

    No Known Activations