© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130338
    Prev
    Next
    INDEX
    Explanations

    curd, turd, purrs

    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_1_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
     informe
    1.30
     are
    1.20
    elijke
    1.08
    t
    1.08
     informes
    1.02
    ονται
    1.00
     compromet
    1.00
     almacenamiento
    0.99
    á
    0.99
     volg
    0.98
    POSITIVE LOGITS
    .
    1.52
    cı
    1.41
    that
    1.27
    at
    1.16
    ↵
    1.15
    H
    1.11
    D
    1.10
    ات
    1.08
    سی
    1.06
    rences
    1.06
    Activations Density 0.001%

    No Known Activations