© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229390
    Prev
    Next
    INDEX
    Explanations

    Meadow or Meadows followed by a descriptor

    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_6_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
    1.36
    ks
    1.06
    fl
    1.01
    z
    1.01
    q
    1.00
    cht
    0.99
    lj
    0.99
    )
    0.95
    1
    0.93
    ver
    0.92
    POSITIVE LOGITS
    다
    0.98
     e
    0.89
    و
    0.82
    ま
    0.82
    ας
    0.80
     have
    0.79
     готови
    0.78
    ↵
    0.76
    ாண்டு
    0.75
     coroner
    0.73
    Activations Density 0.000%

    No Known Activations