© 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
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3330
    Prev
    Next
    INDEX
    Explanations

    instances of the words 'impact' and 'chain' and variants of 'match'

    oai_token-act-pair · gemini-2.0-flash

    impact and chain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    GraphicsUnit
    -0.99
     мәкал
    -0.91
    findpost
    -0.90
    BeginContext
    -0.86
     تضيفلها
    -0.82
    gameserver
    -0.80
    Gambas
    -0.80
    aronder
    -0.79
    =$?
    -0.78
     Мексичка
    -0.77
    POSITIVE LOGITS
    2
    0.75
    1
    0.68
    3
    0.67
    5
    0.67
    4
    0.65
    d
    0.62
    6
    0.61
    i
    0.61
    forma
    0.59
     rodi
    0.58
    Activations Density 0.720%

    No Known Activations