© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6991
    Prev
    Next
    INDEX
    Explanations

    slang, especially instances of "somethin'" and "nothin'"

    oai_token-act-pair · gemini-2.0-flash

    thin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    postsleuth
    -0.60
     način
    -0.54
    schild
    -0.54
     محفوظة
    -0.53
     ritard
    -0.52
    assioned
    -0.52
     Femen
    -0.50
     Hiros
    -0.50
     Ragnar
    -0.49
    ronpa
    -0.49
    POSITIVE LOGITS
     everything
    1.17
    everything
    1.13
    Everything
    1.02
     nothing
    1.02
     Everything
    1.02
    NOTHING
    1.02
    nothing
    1.00
     EVERYTHING
    0.94
     NOTHING
    0.90
     things
    0.88
    Activations Density 0.605%

    No Known Activations