© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233431
    Prev
    Next
    INDEX
    Explanations

    nicht

    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_46_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
     niet
    0.42
    ::$
    0.40
     largely
    0.40
     cnt
    0.39
     meanwhile
    0.39
    |.|
    0.38
     কতক
    0.38
     graciously
    0.38
    antiated
    0.38
    ')],
    0.38
    POSITIVE LOGITS
    Assess
    0.45
    Mons
    0.44
    Rek
    0.40
    做
    0.38
    jek
    0.38
    Bek
    0.38
     Monsieur
    0.37
    Bayern
    0.37
    Alone
    0.37
    jak
    0.37
    Activations Density 0.001%

    No Known Activations