© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3649
    Prev
    Next
    INDEX
    Explanations

    code elements that are named "Listener"

    oai_token-act-pair · gemini-2.0-flash

    Listener

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     in
    -1.20
     a
    -1.19
     an
    -1.17
     the
    -1.12
     
    -1.09
     all
    -0.99
     on
    -0.98
     as
    -0.97
     and
    -0.96
     is
    -0.96
    POSITIVE LOGITS
     ainfi
    1.70
     Theſe
    1.63
     auffi
    1.60
     Jefus
    1.59
     Efq
    1.52
     myſelf
    1.41
     cytok
    1.41
     feroit
    1.40
     ſche
    1.39
     reaſon
    1.38
    Activations Density 2.534%

    No Known Activations