© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197465
    Prev
    Next
    INDEX
    Explanations

    is

    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
     best
    0.49
     least
    0.42
    Least
    0.40
    হ্য
    0.40
     verbs
    0.39
     fre
    0.37
     बेस्ट
    0.37
    亠
    0.37
    受け
    0.37
     wr
    0.37
    POSITIVE LOGITS
    ierrez
    0.40
    Factor
    0.38
     NON
    0.38
    STON
    0.37
     Produ
    0.37
    ாயம்
    0.36
     yelled
    0.36
    শন
    0.36
    leden
    0.35
     Quay
    0.35
    Activations Density 0.001%

    No Known Activations