© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12103
    Prev
    Next
    INDEX
    Explanations

    concrete and reinforced concrete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     石
    0.43
     mềm
    0.42
     STONE
    0.40
    石
    0.39
     đá
    0.39
    穴
    0.39
    Padding
    0.38
     Stones
    0.38
     জাহান
    0.38
    ::-
    0.37
    POSITIVE LOGITS
     concrete
    1.01
    Concrete
    0.93
    concrete
    0.93
     Concrete
    0.89
     concreto
    0.82
     concre
    0.79
     concret
    0.77
     concreta
    0.77
    混凝土
    0.70
     konkret
    0.66
    Activations Density 0.026%

    No Known Activations