© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6615
    Prev
    Next
    INDEX
    Explanations

    somewhat common two- or three-letter words and phrases

    oai_token-act-pair · gemini-2.0-flash

    mere

    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
    UrlResolution
    -0.73
    Bioaccumulative
    -0.69
    TintMode
    -0.68
    Enllaces
    -0.66
    بيوتر
    -0.65
     createState
    -0.64
     vPvB
    -0.63
    writeField
    -0.63
    +#+#
    -0.61
    IUrlHelper
    -0.61
    POSITIVE LOGITS
     Zug
    0.51
    g
    0.47
    zug
    0.45
    enn
    0.44
    jeg
    0.44
     ugy
    0.42
    gy
    0.42
    j
    0.41
    gr
    0.41
    ugc
    0.41
    Activations Density 0.126%

    No Known Activations