© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81215
    Prev
    Next
    INDEX
    Explanations

    head parts

    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_53_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
    ሄ
    0.44
    त्म
    0.41
     সরিয়ে
    0.37
    諸
    0.37
    Loading
    0.36
    Remove
    0.36
    蟻
    0.35
     Admir
    0.35
    streng
    0.35
    濟
    0.35
    POSITIVE LOGITS
     mug
    1.05
     mugs
    1.01
     nog
    0.86
    nog
    0.82
     pe
    0.81
     Mug
    0.80
     mitt
    0.79
     dome
    0.79
     domes
    0.78
    mug
    0.75
    Activations Density 0.001%

    No Known Activations