© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 156841
    Prev
    Next
    INDEX
    Explanations

    pil

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    KeyboardButton
    0.43
    Erin
    0.42
     Кы
    0.40
    প
    0.40
     Эр
    0.39
     Erin
    0.38
    귄
    0.38
     İl
    0.38
     probabilistic
    0.38
    pil
    0.38
    POSITIVE LOGITS
     dangle
    0.43
     dangling
    0.42
    셜
    0.41
    OURCES
    0.40
    cies
    0.40
     Jackie
    0.40
    rogation
    0.39
    Jackie
    0.39
    CIES
    0.39
    Thing
    0.38
    Activations Density 0.000%

    No Known Activations