© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15057
    Prev
    Next
    INDEX
    Explanations

    code related to class structure and definition

    oai_token-act-pair · gemini-2.0-flash

    code/non-English

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     "..\..\
    -0.82
     "..\..\..\
    -0.71
    VIA
    -0.55
    veta
    -0.55
     Mu
    -0.54
    FOUND
    -0.54
     F
    -0.52
     in
    -0.52
     múl
    -0.52
    äinen
    -0.52
    POSITIVE LOGITS
    ագրություններ
    0.65
     DialogInterface
    0.65
    GEBURTS
    0.58
    copg
    0.56
    InjectAttribute
    0.52
     дописавши
    0.52
     linkovi
    0.51
    SceneManagement
    0.50
    Identyfik
    0.49
    fillType
    0.49
    Activations Density 0.317%

    No Known Activations