© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196542
    Prev
    Next
    INDEX
    Explanations

    eventually followed by resolution or action

    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_27_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
     szere
    0.49
     mostr
    0.38
    很大的
    0.37
     قسمت
    0.37
     നി
    0.37
     processes
    0.36
    $~
    0.36
     ㅅ
    0.36
    zig
    0.35
     ძალიან
    0.35
    POSITIVE LOGITS
     hydrolyzed
    0.38
     attributable
    0.37
    órmula
    0.36
    机的
    0.36
     kriv
    0.36
    Offline
    0.35
    指数
    0.34
     vaccinated
    0.34
     numeral
    0.33
     Regener
    0.33
    Activations Density 0.001%

    No Known Activations