© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54448
    Prev
    Next
    INDEX
    Explanations

    electrical properties

    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_55_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
    டித்த
    0.37
    短
    0.37
    SOS
    0.37
     کشمیر
    0.37
    rms
    0.36
    計畫
    0.36
     जर
    0.35
     Perez
    0.35
    akukannya
    0.35
    
    0.35
    POSITIVE LOGITS
     mister
    0.39
     unity
    0.38
     frequencies
    0.38
     প্রমাণ
    0.37
    unbox
    0.36
    ാം
    0.35
     frecuencias
    0.35
     inconven
    0.35
     >=
    0.34
     mate
    0.34
    Activations Density 0.017%

    No Known Activations