© 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. 11729
    Prev
    Next
    INDEX
    Explanations

    technical articles providing some kind of explanation that uses specific jargon often related to mechanics or chemistry

    oai_token-act-pair · gemini-2.0-flash

    modern

    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
     Theſe
    -0.91
     becauſe
    -0.85
     Efq
    -0.80
     Monfieur
    -0.80
    ResumeLayout
    -0.79
     againſt
    -0.78
    "])
    -0.77
     Beſ
    -0.76
     Houſe
    -0.76
    !")
    -0.72
    POSITIVE LOGITS
    ModelBuilder
    0.46
    MigrationBuilder
    0.44
    новништво
    0.43
                   
    0.43
    ContentLoaded
    0.43
    TypedDataSet
    0.42
               
    0.42
     sola
    0.41
    IsContent
    0.41
    init
    0.40
    Activations Density 6.779%

    No Known Activations