Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9579
    Prev
    Next
    INDEX
    Explanations

    historical or biographical information about people and places, especially locations and dates

    oai_token-act-pair · gemini-2.0-flash

    historical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    elemField
    -0.77
     Monfieur
    -0.56
    BufferException
    -0.56
    gameserver
    -0.54
    IVEREF
    -0.53
    rogels
    -0.52
     Theſe
    -0.52
     DHL
    -0.51
     dAtA
    -0.50
     Boeing
    -0.50
    POSITIVE LOGITS
     تضيفلها
    0.62
    ScopeManager
    0.59
    gway
    0.49
     autorytatywna
    0.48
    Mutagenicity
    0.47
     eingestellt
    0.47
     ljudi
    0.46
     patrimoine
    0.45
    Erreferentziak
    0.45
    +:+
    0.45
    Activations Density 17.380%

    No Known Activations