© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6804
    Prev
    Next
    INDEX
    Explanations

    numbers above one

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    2
    -1.20
    1
    -1.18
    5
    -1.10
    3
    -1.09
    9
    -1.05
    6
    -1.05
    0
    -1.02
    7
    -1.02
    4
    -1.02
    8
    -0.99
    POSITIVE LOGITS
    ⓧ
    1.20
    verwijspagina
    1.01
    tagHelperRunner
    1.01
    SequentialGroup
    1.00
     Мексичка
    0.99
     disambiguazione
    0.95
    DoubleQuotes
    0.93
    )";
    0.92
     Efq
    0.92
     oprot
    0.91
    Activations Density 6.338%

    No Known Activations