© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 36428
    Prev
    Next
    INDEX
    Explanations

    calisthenics, tal como

    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_50_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
    ola
    0.40
    olas
    0.40
     tá
    0.39
    comstock
    0.39
     lave
    0.38
    olg
    0.38
    )}-\
    0.38
     타
    0.37
    olen
    0.37
    olin
    0.37
    POSITIVE LOGITS
    izan
    0.46
    indel
    0.41
    िकेट
    0.40
    cij
    0.39
    iza
    0.38
     singularities
    0.38
     POLIT
    0.38
     آباد
    0.38
    CIS
    0.38
     ци
    0.37
    Activations Density 0.005%

    No Known Activations