© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65909
    Prev
    Next
    INDEX
    Explanations

    On

    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_51_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
    __).
    0.40
     fragile
    0.40
     нер
    0.39
    シ
    0.39
    ccedil
    0.38
    Abi
    0.37
     skriver
    0.36
     客
    0.36
     cheeks
    0.35
     Nerve
    0.35
    POSITIVE LOGITS
     Neues
    0.47
    nent
    0.41
    োতে
    0.41
     ross
    0.40
    HPO
    0.40
     Newport
    0.38
    ेंट
    0.38
     उछ
    0.37
    nu
    0.37
    ментов
    0.37
    Activations Density 0.004%

    No Known Activations