© 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. 239288
    Prev
    Next
    INDEX
    Explanations

    continued for

    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
     herewith
    0.40
     Vier
    0.38
     yourselves
    0.37
    itherto
    0.37
    㫻
    0.37
    слав
    0.36
    筛
    0.36
    ṃ
    0.36
    atius
    0.35
     City
    0.35
    POSITIVE LOGITS
    Buffered
    0.38
     પ્રથમ
    0.38
    Contain
    0.38
    Lucida
    0.37
    Cache
    0.36
    イメージ
    0.35
    Functional
    0.35
     rectangular
    0.34
    Composite
    0.34
    임
    0.34
    Activations Density 0.002%

    No Known Activations