© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210740
    Prev
    Next
    INDEX
    Explanations

    Egyptian tombs

    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_43_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
    सम्
    0.40
     Phila
    0.38
    锺
    0.38
    ylmethylsulfanyl
    0.38
    拳
    0.37
    <unused84>
    0.37
    ROOM
    0.37
    grim
    0.37
     Kissinger
    0.36
     racconto
    0.36
    POSITIVE LOGITS
     kilos
    0.42
     kg
    0.41
     motivación
    0.39
     भटक
    0.38
     low
    0.37
    低
    0.37
     motivation
    0.36
     नैतिकता
    0.36
    :";
    0.36
    kg
    0.36
    Activations Density 0.002%

    No Known Activations