© 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-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 2905
    Prev
    Next
    INDEX
    Explanations

    reasoning, often in the form of argument or persuasion, toward some possible or imagined action, or questioning actions

    oai_token-act-pair · gemini-2.0-flash

    Analytical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     place
    -0.77
    place
    -0.73
    Places
    -0.66
     Places
    -0.63
     HasFactory
    -0.61
     places
    -0.60
     PLACE
    -0.60
     Place
    -0.59
    Tē
    -0.57
     PLACES
    -0.57
    POSITIVE LOGITS
    éez
    0.57
     <<<<<<<<<<<<<<
    0.52
     الرياضيه
    0.50
     Chwiliwch
    0.48
    opla
    0.48
    SharedCtor
    0.47
    zini
    0.47
    ogs
    0.47
    AndEndTag
    0.47
    enegro
    0.46
    Activations Density 4.410%

    No Known Activations