© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167925
    Prev
    Next
    INDEX
    Explanations

    imaginary

    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_56_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
     /
    0.49
     /,
    0.38
    ／
    0.36
     functions
    0.34
    ophytic
    0.34
    -/
    0.33
    /"
    0.33
    ोनेशिया
    0.33
     derived
    0.32
     WORKS
    0.32
    POSITIVE LOGITS
    日本人
    0.33
    ​
    0.32
     Asians
    0.31
    逮
    0.31
    রাং
    0.31
     hik
    0.31
    ल्टी
    0.30
     Africans
    0.30
    rees
    0.30
     있다는
    0.30
    Activations Density 0.002%

    No Known Activations