© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206584
    Prev
    Next
    INDEX
    Explanations

    years of experience and qualifications

    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_25_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
     dirección
    0.43
     vuelve
    0.41
    )=-
    0.40
    órc
    0.40
    endaftaran
    0.39
    哈
    0.38
    irection
    0.38
     presión
    0.38
     ocurrido
    0.38
    डिंग
    0.37
    POSITIVE LOGITS
     envisage
    0.37
     observer
    0.37
    Ǻ
    0.35
     dipped
    0.35
     Countries
    0.35
     envisaged
    0.35
     Journalists
    0.35
     childish
    0.34
     possess
    0.34
     Fifty
    0.34
    Activations Density 0.001%

    No Known Activations