© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10309
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     lumea
    -0.52
    нциклопе
    -0.43
     Umgang
    -0.41
    FromJson
    -0.41
     Zurück
    -0.40
     зара
    -0.39
    провод
    -0.39
     innamor
    -0.39
     وصلة
    -0.39
     equipes
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.93
     AttributeSet
    0.84
     الحره
    0.71
     disambiguazione
    0.68
     ModelExpression
    0.65
    IndentedString
    0.63
    RegressionTest
    0.62
    GTCX
    0.61
    TagHelper
    0.60
    EDEFAULT
    0.59
    Activations Density 3.697%

    No Known Activations