© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122786
    Prev
    Next
    INDEX
    Explanations

    latex figure environment

    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_37_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
     ஹ
    0.38
    ismod
    0.37
    mass
    0.37
     highlighted
    0.36
    特色
    0.36
    cott
    0.35
    బర్
    0.35
    Sung
    0.34
    mented
    0.34
    rez
    0.34
    POSITIVE LOGITS
     চিত্র
    0.47
    銅
    0.41
     figure
    0.41
     картина
    0.40
    нить
    0.39
    гация
    0.39
     altına
    0.39
     cadena
    0.38
     bý
    0.38
     figura
    0.38
    Activations Density 0.001%

    No Known Activations