© 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. 53336
    Prev
    Next
    INDEX
    Explanations

    interested

    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
     Explained
    0.41
    ใน
    0.38
    pathname
    0.38
     apprehension
    0.38
     ইউনিভার্সিটি
    0.38
    ഞ്ഞെടു
    0.37
    山田
    0.37
    
    0.36
     hobbies
    0.36
    торой
    0.36
    POSITIVE LOGITS
     habitantes
    0.39
     differently
    0.37
    genstein
    0.37
     विषय
    0.36
     लगती
    0.36
    ethe
    0.36
     inhabitants
    0.36
     Боли
    0.36
    olic
    0.36
    ólica
    0.36
    Activations Density 0.007%

    No Known Activations