© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13251
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially those assigning values to output variables or discussing error handling.

    oai_token-act-pair · gemini-2.0-flash

    output

    np_max-act-logits · 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
    évaluateur
    -0.89
     صوتيه
    -0.76
     مرئيه
    -0.75
    )\}
    -0.62
     يتيمه
    -0.62
     ),
    -0.61
    verwijspagina
    -0.61
     المعيارى
    -0.61
    ])]
    -0.60
    hyrchwyd
    -0.60
    POSITIVE LOGITS
    RefNanny
    0.56
    swt
    0.47
    borne
    0.46
     못
    0.46
    leaved
    0.45
    featureID
    0.44
     CURIAM
    0.44
     Pu
    0.44
    illy
    0.44
    Пу
    0.44
    Activations Density 4.146%

    No Known Activations