© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13464
    Prev
    Next
    INDEX
    Explanations

    words related to mathematical or linguistic modifications

    oai_token-act-pair · gemini-2.0-flash

    Transformations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    WebMethod
    -0.49
     Capital
    -0.44
     Horv
    -0.43
    lenen
    -0.42
     Gross
    -0.41
     empleo
    -0.41
     —
    -0.40
     un
    -0.40
     rigu
    -0.40
    ;
    -0.40
    POSITIVE LOGITS
     transformations
    1.16
     transformation
    1.14
     متعلقه
    1.07
     Transformation
    1.07
     transformed
    1.05
    ſelf
    1.05
     transforming
    1.05
     transforma
    1.00
     Transformations
    0.99
     itſelf
    0.98
    Activations Density 0.632%

    No Known Activations