© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11915
    Prev
    Next
    INDEX
    Explanations

    pronouns and the words around them

    oai_token-act-pair · gemini-2.0-flash

    excerpts from various texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     newOwner
    -1.02
    StoryboardSegue
    -0.90
    AndEndTag
    -0.86
    }\]
    -0.85
    MENAFN
    -0.84
    featureID
    -0.82
     disambiguazione
    -0.79
    enderror
    -0.78
     Drapeau
    -0.77
     <>",
    -0.77
    POSITIVE LOGITS
     pre
    0.40
     re
    0.40
     a
    0.40
    by
    0.40
     direct
    0.40
     go
    0.40
    <
    0.40
     to
    0.39
    th
    0.38
     (
    0.38
    Activations Density 3.628%

    No Known Activations