© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    4. 80454
    Prev
    Next
    INDEX
    Explanations

    materials countermeasures

    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
    棌
    0.48
    인더
    0.43
     INSTITUTE
    0.40
    Institute
    0.39
     Institute
    0.38
    ICA
    0.38
    Jonathan
    0.38
    institute
    0.37
    ieder
    0.37
    Anast
    0.37
    POSITIVE LOGITS
     материалов
    0.42
    >(&
    0.38
    ៣
    0.38
    អស់
    0.37
     explosion
    0.37
     BF
    0.37
    ὧ
    0.37
    ייל
    0.37
     materials
    0.37
     countermeasures
    0.36
    Activations Density 0.016%

    No Known Activations