© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110111
    Prev
    Next
    INDEX
    Explanations

    OS followed by specific suffixes or phrases

    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_2_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
     in
    1.50
     is
    1.33
     not
    1.02
    </h2>
    1.01
     في
    0.99
    ам
    0.96
     t
    0.95
    Ü
    0.95
    ай
    0.93
    </h4>
    0.93
    POSITIVE LOGITS
    d
    1.61
    i
    1.60
    m
    1.49
    it
    1.41
    n
    1.34
    ni
    1.34
    3
    1.30
    iul
    1.22
    ng
    1.21
    that
    1.21
    Activations Density 0.001%

    No Known Activations