© 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. 5089
    Prev
    Next
    INDEX
    Explanations

    mentions of something that either deserves or does not deserve respect or attention

    oai_token-act-pair · gemini-2.0-flash

    "des"

    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
    ValueStyle
    -0.81
    UnusedPrivate
    -0.75
    tagHelperRunner
    -0.75
     deserved
    -0.74
    localctx
    -0.73
    存于互联网档案馆
    -0.72
    fjspx
    -0.69
     newBuilder
    -0.69
    İstinadlar
    -0.66
    antMatchers
    -0.65
    POSITIVE LOGITS
    des
    0.66
     Des
    0.65
     des
    0.65
    Des
    0.64
     DES
    0.59
    DES
    0.57
     desar
    0.53
    dese
    0.45
     Dok
    0.45
     Doc
    0.43
    Activations Density 2.569%

    No Known Activations