© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146620
    Prev
    Next
    INDEX
    Explanations

    chess openings: e4, openings

    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_18_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
    k
    0.63
    ed
    0.55
    ivers
    0.48
    ”。
    0.48
    ut
    0.47
    nj
    0.46
    r
    0.46
    aded
    0.45
    c
    0.45
    b
    0.45
    POSITIVE LOGITS
     capsid
    0.55
     rebounding
    0.52
    ัพท์
    0.50
     tendon
    0.50
    텐츠
    0.49
    лень
    0.49
     ransomware
    0.47
     ribosome
    0.47
     cytosol
    0.47
     identifying
    0.46
    Activations Density 0.001%

    No Known Activations