© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13524
    Prev
    Next
    INDEX
    Explanations

    colors and cuisines

    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_13_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
     specialize
    0.46
    𝐄
    0.45
    V
    0.43
     oth
    0.42
    วัสดี
    0.42
     rosto
    0.41
    ET
    0.41
    E
    0.41
     加
    0.39
     પૂ
    0.39
    POSITIVE LOGITS
     Valuation
    0.31
    cose
    0.31
    periode
    0.30
    Concluding
    0.30
    l
    0.30
    icity
    0.29
     अवकाश
    0.29
    onium
    0.29
    anlage
    0.29
    ליה
    0.28
    Activations Density 0.204%

    No Known Activations