© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14716
    Prev
    Next
    INDEX
    Explanations

    someone wanting to hear something or the action of hearing in a legal/political context.

    oai_token-act-pair · gemini-2.0-flash

    listening

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     listen
    -2.89
     listening
    -2.89
     listened
    -2.75
     Listen
    -2.67
     listens
    -2.66
     hearing
    -2.64
     Listening
    -2.61
     hear
    -2.55
    Listen
    -2.47
    Listening
    -2.42
    POSITIVE LOGITS
    
    0.56
    StructEnd
    0.55
    parsedMessage
    0.48
    Personensuche
    0.48
     otomatig
    0.47
    ęcia
    0.47
    󠁣
    0.44
    annique
    0.44
    DeleteBehavior
    0.44
    horst
    0.44
    Activations Density 3.167%

    No Known Activations