© 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. 32827
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    টিকে
    0.40
    十九章
    0.38
    нется
    0.35
    なくて
    0.35
    ётся
    0.35
     Ă
    0.35
    ίου
    0.34
     거라고
    0.34
    SelectSingleNode
    0.34
    ября
    0.33
    POSITIVE LOGITS
    uur
    0.47
     -.
    0.47
    uale
    0.46
    _-
    0.44
    ue
    0.43
    uer
    0.41
    theo
    0.41
     lym
    0.41
     -"
    0.41
    aredo
    0.40
    Activations Density 0.009%

    No Known Activations