© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195239
    Prev
    Next
    INDEX
    Explanations

    your database credentials

    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_27_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
    substring
    0.34
     причи
    0.34
    pesas
    0.34
     Moraes
    0.34
    麻烦
    0.33
    ಫ
    0.32
     Painters
    0.32
     iunie
    0.32
    활
    0.32
    פע
    0.32
    POSITIVE LOGITS
    ByType
    0.42
    Kalb
    0.38
     benar
    0.38
    IAMS
    0.37
    INVEST
    0.37
    idges
    0.36
     begged
    0.36
    روں
    0.36
     invincible
    0.36
     larch
    0.35
    Activations Density 0.001%

    No Known Activations