© 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. 167878
    Prev
    Next
    INDEX
    Explanations

    ab

    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
    Routine
    0.38
     আলে
    0.36
    ౌ
    0.35
    Vy
    0.33
     लिहि
    0.33
    ㅈ
    0.33
    総合
    0.32
    દ
    0.32
     attacker
    0.32
    jap
    0.32
    POSITIVE LOGITS
     Ab
    1.60
    Ab
    1.27
    ab
    0.81
     Аб
    0.70
     الاب
    0.66
     ab
    0.65
     अभ
    0.62
     اب
    0.60
     أب
    0.58
     Af
    0.57
    Activations Density 0.006%

    No Known Activations