© 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. 4834
    Prev
    Next
    INDEX
    Explanations

    programming code, place names with "de la", and the phrase, "of the valley"

    oai_token-act-pair · gemini-2.0-flash

    Text with metadata

    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
     composite
    -0.49
    ,
    -0.48
     
    -0.48
    X
    -0.47
     >
    -0.47
     best
    -0.47
     I
    -0.46
    »
    -0.46
    ]
    -0.45
    S
    -0.45
    POSITIVE LOGITS
    sizeCache
    1.41
     فريبيس
    1.23
    الدراسه
    1.22
     يتيمه
    1.19
     GenerationType
    1.13
     '\\;'
    1.13
    ContentAlignment
    1.13
    webElementGuid
    1.13
     wireType
    1.07
    featureID
    1.07
    Activations Density 1.559%

    No Known Activations