© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140467
    Prev
    Next
    INDEX
    Explanations

    atomic mass unit (amu) and atomic number

    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_12_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
     autorizado
    0.56
     цін
    0.52
     depreci
    0.51
     выигра
    0.50
     relatable
    0.50
     מז
    0.48
     cantik
    0.48
    <0x80>
    0.47
     конку
    0.47
     revamp
    0.47
    POSITIVE LOGITS
     Darkness
    0.57
    sing
    0.56
    }()
    0.54
    ئو
    0.53
    ignons
    0.53
    ;}
    0.52
     ت
    0.51
    }$.
    0.51
    contact
    0.51
    oring
    0.50
    Activations Density 0.003%

    No Known Activations