© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11673
    Prev
    Next
    INDEX
    Explanations

    memory hierarchy and systems

    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_13_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
     конструкции
    0.46
    Flights
    0.43
    佰
    0.42
     дизайна
    0.42
     emble
    0.42
    ഴിലാ
    0.41
     Flights
    0.41
     mesmos
    0.41
     esemplari
    0.41
    Comb
    0.40
    POSITIVE LOGITS
    her
    0.57
    this
    0.56
     this
    0.55
     her
    0.51
    onu
    0.50
     questioned
    0.48
    Q
    0.48
    šina
    0.47
     bidding
    0.47
     victory
    0.45
    Activations Density 0.039%

    No Known Activations