© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4174
    Prev
    Next
    INDEX
    Explanations

    code and programming terms

    oai_token-act-pair · gemini-2.0-flash

    head begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    +#+#
    -0.55
    extAlignment
    -0.50
    PutMapping
    -0.49
    НР
    -0.45
    Климат
    -0.45
     корзи
    -0.44
     zd
    -0.43
    avut
    -0.43
    jsii
    -0.42
    CardModule
    -0.42
    POSITIVE LOGITS
     beginnetje
    0.63
     pinulongan
    0.61
    %)$
    0.60
     rêves
    0.58
    cipl
    0.55
    culous
    0.53
    તે
    0.53
    ughty
    0.52
     OFDb
    0.52
     ModelExpression
    0.52
    Activations Density 6.489%

    No Known Activations