© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9192
    Prev
    Next
    INDEX
    Explanations

    code with conditional statements and object oriented programming like use of inheritance.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     kasarigan
    -0.75
    EDEFAULT
    -0.59
     Waray
    -0.56
     tadi
    -0.53
     ujednoznacz
    -0.53
    GHIJKLM
    -0.53
    новништво
    -0.52
    jaros
    -0.52
     նաև
    -0.52
     trajets
    -0.51
    POSITIVE LOGITS
    enumi
    0.64
     JAXBElement
    0.58
    tagHelperRunner
    0.58
    AppMethodBeat
    0.56
    setVerticalGroup
    0.53
    InitVars
    0.52
    ConfigureAwait
    0.50
    Välislingid
    0.49
    TableBody
    0.48
    ISupport
    0.47
    Activations Density 1.063%

    No Known Activations