© 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-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9653
    Prev
    Next
    INDEX
    Explanations

    Def

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    wa
    0.73
     whe
    0.73
    вт
    0.73
     reloading
    0.72
    adro
    0.71
    fair
    0.67
    锉
    0.67
    doğan
    0.65
     Nearly
    0.65
     Cuv
    0.64
    POSITIVE LOGITS
    iciency
    0.84
    icient
    0.71
    lorescence
    0.70
    轶
    0.69
    ripsi
    0.64
    ිය
    0.63
    اوم
    0.62
     esemplari
    0.62
     обеспечить
    0.62
    initions
    0.62
    Activations Density 0.005%

    No Known Activations