© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    Hibernate or Hib

    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_40_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
    ía
    0.42
     registry
    0.39
    CommandLine
    0.39
     unsteady
    0.39
    mfrac
    0.38
     registries
    0.38
     continuity
    0.38
     (++
    0.38
     hệ
    0.37
     നെ
    0.37
    POSITIVE LOGITS
    industrial
    0.38
    俢
    0.38
    trivia
    0.38
    Hint
    0.37
     अनिवार्य
    0.37
    тяну
    0.37
    otika
    0.36
    reactive
    0.35
     Hint
    0.35
    hints
    0.35
    Activations Density 0.000%

    No Known Activations