© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81005
    Prev
    Next
    INDEX
    Explanations

    against

    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_53_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
     बि
    0.40
     setResult
    0.36
     собой
    0.35
    িপ্ত
    0.35
    ＮＡ
    0.35
     pen
    0.35
     겁
    0.33
     incumpl
    0.32
    ራ
    0.32
    菪
    0.32
    POSITIVE LOGITS
     against
    3.00
    against
    2.81
    Against
    2.80
     Against
    2.73
     gegen
    2.47
     против
    2.41
     AGAINST
    2.38
     tegen
    2.25
     ضد
    2.23
     contre
    2.20
    Activations Density 0.466%

    No Known Activations