© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 7438
    Prev
    Next
    INDEX
    Explanations

    text related to conferences, especially attendance/participation

    oai_token-act-pair · gemini-2.0-flash

    conferences and meetings

    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
     conference
    -2.41
     Conference
    -2.16
    Conference
    -2.14
     conferences
    -2.06
     CONFERENCE
    -2.00
    conference
    -1.98
     Conferences
    -1.82
     convention
    -1.57
     conferencia
    -1.45
     konfer
    -1.40
    POSITIVE LOGITS
    olingo
    0.58
    ("")]
    
    0.53
    WriteLiteral
    0.50
    textTheme
    0.49
    HtmlAttribute
    0.48
    <?
    0.47
     recast
    0.45
     Epit
    0.45
    Epit
    0.45
    kmale
    0.45
    Activations Density 2.154%

    No Known Activations