© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13657
    Prev
    Next
    INDEX
    Explanations

    first person pronouns and contractions

    oai_token-act-pair · gemini-2.0-flash

    fear

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    initComponents
    -0.59
     مشين
    -0.54
    Persist
    -0.52
     convertView
    -0.51
    metto
    -0.50
    Attribution
    -0.50
    Concurrency
    -0.50
    schild
    -0.47
     shed
    -0.46
    indd
    -0.46
    POSITIVE LOGITS
     afraid
    1.95
     Afraid
    1.38
     fear
    1.25
    fraid
    1.18
    Fear
    1.05
    fear
    1.05
     Fear
    1.04
     fears
    1.02
     feared
    0.94
     FEAR
    0.93
    Activations Density 2.161%

    No Known Activations