© 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. 5128
    Prev
    Next
    INDEX
    Explanations

    general banter in informal language, possibly AAVE.

    oai_token-act-pair · gemini-2.0-flash

    Informal writing

    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
     dis
    -0.93
     d
    -0.88
     da
    -0.84
     de
    -0.84
     ur
    -0.82
     dem
    -0.71
    dis
    -0.63
     Ur
    -0.63
    MLLoader
    -0.62
     dese
    -0.60
    POSITIVE LOGITS
     houſe
    0.73
     ſel
    0.71
     greateſt
    0.70
     ſta
    0.68
    ContentAsync
    0.68
     ſtate
    0.67
     uſe
    0.67
     raiſ
    0.66
     ſtand
    0.66
    ſelves
    0.66
    Activations Density 0.872%

    No Known Activations