© 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. 246070
    Prev
    Next
    INDEX
    Explanations

    CSS height properties

    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
    ᱕
    0.39
    ᱗
    0.39
     Sid
    0.38
    idE
    0.38
    价比
    0.37
     idE
    0.36
    7
    0.36
     embracing
    0.36
    पहर
    0.36
     ஏழு
    0.36
    POSITIVE LOGITS
     LAD
    0.41
    hoven
    0.37
    鰤
    0.37
    कट
    0.37
    olon
    0.36
     BN
    0.35
    ભ્ય
    0.35
    ibold
    0.35
    ми
    0.35
    cur
    0.34
    Activations Density 0.001%

    No Known Activations