© 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
    2. Gemma-3-27B-IT
    3. 14-GEMMASCOPE-2-TRANSCODER-262K
    4. 99620
    Prev
    Next
    INDEX
    Explanations

    ISBN and DOI identifiers

    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_14_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
    U
    0.61
    ScriptAssemblies
    0.57
     रावत
    0.56
     ग्लू
    0.55
    }`,
    0.54
    ningar
    0.54
     McGraw
    0.54
    utches
    0.52
    सेज
    0.52
    Ꮋ
    0.51
    POSITIVE LOGITS
    נה
    0.55
     considers
    0.55
     celebrates
    0.54
     começa
    0.53
     proposes
    0.52
     comienza
    0.52
     занимается
    0.50
     characterizes
    0.50
     বাঙ্গালীর
    0.50
     desafios
    0.49
    Activations Density 0.000%

    No Known Activations