© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14269
    Prev
    Next
    INDEX
    Explanations

    code related to Angular components and RxJS Observables

    oai_token-act-pair · gemini-2.0-flash

    Code and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     MonoBehaviour
    -0.77
     Philist
    -0.76
    ंदीखरीदारी
    -0.75
     Masih
    -0.72
    #+#
    -0.72
     tearDown
    -0.69
    didSet
    -0.69
    +#+
    -0.69
     itſelf
    -0.68
     snippetHide
    -0.68
    POSITIVE LOGITS
     At
    0.36
    entieth
    0.36
     informes
    0.33
    editForm
    0.33
     tajam
    0.32
    webElementXpaths
    0.31
     Ang
    0.31
    MODULE
    0.30
    .,
    0.29
    Progress
    0.29
    Activations Density 10.683%

    No Known Activations