© 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. 215288
    Prev
    Next
    INDEX
    Explanations

    names

    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
    GSM
    0.41
     Aron
    0.40
     barista
    0.40
     συγκ
    0.40
    Mamm
    0.40
    গতি
    0.40
    🎀
    0.39
     cond
    0.39
     Guggenheim
    0.39
     Seung
    0.39
    POSITIVE LOGITS
     POD
    0.42
    POD
    0.41
     Kle
    0.37
    azure
    0.37
    차
    0.37
     Roder
    0.36
     KLE
    0.36
     Подо
    0.36
    Kle
    0.36
     Ferro
    0.36
    Activations Density 0.005%

    No Known Activations