© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140199
    Prev
    Next
    INDEX
    Explanations

    collector cars

    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_46_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
     tuning
    0.54
     Tuning
    0.50
     tunable
    0.49
    Tune
    0.47
     tuned
    0.45
    튠
    0.43
     tune
    0.43
    tuned
    0.42
     Tune
    0.41
     Tun
    0.41
    POSITIVE LOGITS
     Decomposition
    0.36
    arlier
    0.36
     式
    0.36
    ଳ
    0.35
     बर
    0.35
    ンドウ
    0.35
    澱
    0.34
     Phương
    0.34
     వ్యా
    0.33
    权利
    0.33
    Activations Density 0.000%

    No Known Activations