© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    4. 165575
    Prev
    Next
    INDEX
    Explanations

    rest when you need to

    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_34_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
    कर्ता
    0.44
    因為
    0.41
    跪
    0.41
     Cosm
    0.40
     relaxing
    0.40
     Sadd
    0.39
    Jas
    0.38
    因为
    0.38
    Jos
    0.38
    Tarea
    0.38
    POSITIVE LOGITS
    igung
    0.43
     rivals
    0.43
    猛
    0.39
    ked
    0.36
     metall
    0.36
     equations
    0.36
    idental
    0.36
     elif
    0.36
     portraits
    0.36
     rival
    0.35
    Activations Density 0.002%

    No Known Activations