© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50314
    Prev
    Next
    INDEX
    Explanations

    ships and voyages

    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_55_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
     yoke
    0.37
    弱
    0.37
     Filing
    0.36
     thinker
    0.36
     modeller
    0.35
    qx
    0.35
     player
    0.34
     കീ
    0.34
     Reth
    0.34
     кей
    0.34
    POSITIVE LOGITS
    ubber
    0.39
    itano
    0.38
     ٣
    0.38
    Active
    0.37
    Experiment
    0.37
    阏
    0.37
     experimenting
    0.36
     তৎপর
    0.36
     ساين
    0.36
    akuan
    0.36
    Activations Density 0.001%

    No Known Activations