© 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. 32875
    Prev
    Next
    INDEX
    Explanations

    Intrigue and tragedy

    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
    ff
    0.41
    爛
    0.38
    čak
    0.38
    de
    0.37
    eff
    0.37
     Saka
    0.37
    efficients
    0.36
     سخ
    0.36
    حي
    0.36
     Sä
    0.36
    POSITIVE LOGITS
    во
    0.58
    uated
    0.45
     voicing
    0.44
    ВО
    0.43
     gên
    0.42
     Geg
    0.39
    <0x16>
    0.39
    vo
    0.39
    uen
    0.39
    uten
    0.38
    Activations Density 0.011%

    No Known Activations