© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219042
    Prev
    Next
    INDEX
    Explanations

    bottled water

    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_47_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
     mineral
    3.13
     Mineral
    2.88
    Mineral
    2.84
    mineral
    2.81
     минера
    2.67
     MINERAL
    2.47
    矿
    2.19
    礦
    2.11
     minerales
    2.06
     खनिज
    2.03
    POSITIVE LOGITS
     डेविड
    0.37
     TP
    0.37
     गवा
    0.37
     जया
    0.36
    []>
    0.36
    バイス
    0.36
     व्यावहारिक
    0.36
    ➞
    0.36
     parip
    0.35
    ColumnKind
    0.35
    Activations Density 0.002%

    No Known Activations