© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4475
    Prev
    Next
    INDEX
    Explanations

    uses of the word "after" and other words often used in connection with it at lower activation levels.

    oai_token-act-pair · gemini-2.0-flash

    after

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ^(@)
    -0.80
     GoogleFonts
    -0.77
    HostException
    -0.75
     {?}
    -0.73
    enumii
    -0.73
     piattaforma
    -0.69
     prossima
    -0.69
     imprimée
    -0.69
     réguli
    -0.68
     برانيه
    -0.68
    POSITIVE LOGITS
     being
    0.72
     fiind
    0.49
     getting
    0.46
     eint
    0.41
     expli
    0.41
    being
    0.40
    ppus
    0.40
     having
    0.39
     enjoying
    0.39
    pref
    0.39
    Activations Density 5.187%

    No Known Activations