© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59588
    Prev
    Next
    INDEX
    Explanations

    tabloid rag

    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_11_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
    ä
    0.64
    AN
    0.56
    g
    0.54
    গ
    0.54
    agé
    0.53
    or
    0.52
    It
    0.52
    Its
    0.52
    ikli
    0.51
    𝙜
    0.51
    POSITIVE LOGITS
     comportamenti
    0.63
     tiem
    0.59
    ﻄ
    0.59
    🚦
    0.59
     repentance
    0.57
     scoot
    0.57
    examination
    0.57
     ठोस
    0.57
     exame
    0.56
    цов
    0.55
    Activations Density 0.001%

    No Known Activations