© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84079
    Prev
    Next
    INDEX
    Explanations

    héroe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    al
    2.05
    de
    1.86
    的
    1.81
    z
    1.74
    ch
    1.66
    س
    1.63
    在
    1.59
    用
    1.46
    ka
    1.38
    re
    1.37
    POSITIVE LOGITS
    یم
    1.65
     recib
    1.59
    یر
    1.53
     powied
    1.49
     avaient
    1.47
     obten
    1.46
     anunci
    1.41
     analiz
    1.41
     seguros
    1.41
     empez
    1.41
    Activations Density 0.000%

    No Known Activations