© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37309
    Prev
    Next
    INDEX
    Explanations

    model

    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_57_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
     صغير
    0.41
     panel
    0.39
     PANEL
    0.38
     पैनल
    0.38
    Panel
    0.37
     Legal
    0.37
    ือน
    0.37
    ↝
    0.36
     profile
    0.36
    rency
    0.36
    POSITIVE LOGITS
     indeed
    1.20
    indeed
    1.09
     truth
    1.05
     Indeed
    1.02
    Indeed
    1.01
    truth
    1.01
     Truth
    0.93
    Truth
    0.88
     verdad
    0.84
     verità
    0.83
    Activations Density 0.007%

    No Known Activations