© 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. 130153
    Prev
    Next
    INDEX
    Explanations

    Swedish mixed language

    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
     bol
    0.57
     hold
    0.54
     Bol
    0.54
     HOLD
    0.52
     Hold
    0.49
    Bol
    0.49
    持
    0.48
     बोल
    0.47
    を持
    0.47
     볼
    0.46
    POSITIVE LOGITS
    plum
    0.44
     latt
    0.43
    ຕົ
    0.42
     kl
    0.39
    ulates
    0.39
     FNA
    0.39
    पत
    0.38
     liné
    0.38
    肾
    0.38
    gunta
    0.37
    Activations Density 0.000%

    No Known Activations