© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16378
    Prev
    Next
    INDEX
    Explanations

    words that indicate subjective feelings and opinions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Constellation
    -0.51
    Scénario
    -0.49
     RPS
    -0.47
    AccessLevel
    -0.47
    interceptor
    -0.47
    TRIBUN
    -0.46
     DMR
    -0.45
     CSP
    -0.45
     extrapolation
    -0.45
     volatile
    -0.45
    POSITIVE LOGITS
     pitié
    0.70
     enfans
    0.69
     âgées
    0.68
     fermés
    0.65
     démocr
    0.64
     blessés
    0.64
     précédents
    0.63
     avoient
    0.62
    paravant
    0.61
     prisonniers
    0.60
    Activations Density 32.593%

    No Known Activations