© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48494
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    锛
    0.42
    <(),
    0.40
    থ্যা
    0.39
    searchDisplay
    0.38
     संजय
    0.37
    lollipop
    0.37
     antisymmetric
    0.37
    Mkv
    0.37
    ogeneity
    0.37
    ChartView
    0.36
    POSITIVE LOGITS
     Rand
    0.37
     PLUS
    0.36
     إليها
    0.35
     그리고
    0.35
     LESS
    0.35
    关
    0.35
     Leslie
    0.34
     注
    0.34
     Distress
    0.34
    isRequired
    0.33
    Activations Density 0.002%

    No Known Activations