© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200490
    Prev
    Next
    INDEX
    Explanations

    names of brands

    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
    berg
    0.51
    BERG
    0.50
     Cap
    0.47
    Berg
    0.46
    Kurt
    0.46
    bergs
    0.44
    Cap
    0.41
    丳
    0.41
    ocap
    0.40
     Berg
    0.39
    POSITIVE LOGITS
    朊
    0.41
    ỉnh
    0.36
    DLE
    0.36
     번
    0.36
    avos
    0.36
    ぇ
    0.36
     subversive
    0.36
    اید
    0.35
     अनियमित
    0.35
     निवडणुकी
    0.35
    Activations Density 0.003%

    No Known Activations