© 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. 67170
    Prev
    Next
    INDEX
    Explanations

    rs

    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
    omal
    0.39
     Loop
    0.39
    xf
    0.36
     overcame
    0.36
     length
    0.35
     depress
    0.35
     crane
    0.35
    ວ
    0.34
     bills
    0.34
     മരണ
    0.34
    POSITIVE LOGITS
    দেন
    0.42
    iento
    0.41
    गंध
    0.40
    Inspection
    0.40
    ENSATION
    0.39
    Policy
    0.38
    Kang
    0.38
     アウター
    0.38
    გან
    0.38
    锂
    0.38
    Activations Density 0.000%

    No Known Activations