© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6058
    Prev
    Next
    INDEX
    Explanations

    the word "submit" as well as words meaning initial or apologetic

    oai_token-act-pair · gemini-2.0-flash

    submit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -1.15
     a
    -0.92
     an
    -0.91
     
    -0.84
     some
    -0.84
     several
    -0.82
     in
    -0.80
     very
    -0.79
     this
    -0.78
     his
    -0.76
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    1.47
     feroit
    1.42
    findpost
    1.42
     CreateTagHelper
    1.38
    tvguidetime
    1.34
     pouvoit
    1.30
     auroit
    1.30
    IUrlHelper
    1.24
     ainfi
    1.23
    CppMethod
    1.21
    Activations Density 1.043%

    No Known Activations