© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2002
    Prev
    Next
    INDEX
    Explanations

    Kas, Kash, Kos, ヰ

    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_39_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
    样的
    0.41
    ]，
    0.37
     victoria
    0.35
    ivariable
    0.34
     bir
    0.34
     '--
    0.33
     hinaus
    0.33
     নাগ
    0.33
     الانتق
    0.32
    夫妇
    0.32
    POSITIVE LOGITS
     Kas
    0.39
    ヰ
    0.39
    ōu
    0.39
     사람이
    0.38
    മിക
    0.37
     escolh
    0.36
    ncols
    0.36
     posteriorly
    0.35
     Poste
    0.35
    篦
    0.35
    Activations Density 0.020%

    No Known Activations