© 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. 3977
    Prev
    Next
    INDEX
    Explanations

    JSON data that contains names and prices

    oai_token-act-pair · gemini-2.0-flash

    Punctuation marks

    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
    AddTagHelper
    -0.81
     متعلقه
    -0.71
     betweenstory
    -0.67
    :+:
    -0.67
    CPtr
    -0.67
    WarningLevel
    -0.65
    principalColumn
    -0.62
    #+#
    -0.58
    RegressionTest
    -0.57
    ंदीखरीदारी
    -0.57
    POSITIVE LOGITS
    VELOP
    0.59
     nød
    0.58
    <bos>
    0.58
     logistique
    0.55
    ’.”
    0.55
     escalier
    0.55
     riscal
    0.54
     miroir
    0.53
     régl
    0.53
     feroit
    0.52
    Activations Density 5.762%

    No Known Activations