© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34659
    Prev
    Next
    INDEX
    Explanations

    them/their

    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
    re
    0.80
    ere
    0.77
    RE
    0.66
    ERE
    0.66
    ére
    0.61
    ère
    0.61
    ре
    0.58
    y
    0.54
     ere
    0.53
    rea
    0.49
    POSITIVE LOGITS
     heir
    0.73
     Heir
    0.60
    θε
    0.50
     ther
    0.49
     heirloom
    0.45
    uir
    0.44
    nick
    0.42
    IsEnabled
    0.42
    thm
    0.42
     Θε
    0.42
    Activations Density 0.347%

    No Known Activations