© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 13651
    Prev
    Next
    INDEX
    Explanations

    the word "of" preceding nouns and concepts related to quantities and natural formations

    oai_token-act-pair · gemini-2.0-flash

    negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    StructEnd
    -0.55
    ValueGeneration
    -0.47
     internetowa
    -0.46
    soort
    -0.46
    MLLoader
    -0.42
    verifyException
    -0.41
     ?>
    
    -0.40
     بيها
    -0.39
    TagMode
    -0.39
     Vallarta
    -0.39
    POSITIVE LOGITS
    Portály
    0.65
    ValueStyle
    0.65
     CreateTagHelper
    0.62
     studier
    0.59
     esternos
    0.59
    Portale
    0.58
    ariats
    0.58
    ciaal
    0.57
     समीक्षाओं
    0.57
    QMetaType
    0.56
    Activations Density 1.554%

    No Known Activations