© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179034
    Prev
    Next
    INDEX
    Explanations

    Cor

    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
     Deluxe
    0.43
    ടുത
    0.43
    deceased
    0.42
    ぁ
    0.41
    riram
    0.38
    ギ
    0.38
    geschossiges
    0.38
     الده
    0.37
    쯔
    0.36
    营业
    0.36
    POSITIVE LOGITS
     pul
    0.44
     Pul
    0.38
    ondes
    0.38
     amal
    0.38
     Rasa
    0.38
    脈
    0.37
     ras
    0.37
    ONOM
    0.37
     herv
    0.36
     आंव
    0.36
    Activations Density 0.000%

    No Known Activations