© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6375
    Prev
    Next
    INDEX
    Explanations

    instances of people having a personal experience or expressing knowledge, ability, or emotional state.

    oai_token-act-pair · gemini-2.0-flash

    exactly

    np_max-act-logits · 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
     ostavi
    -0.54
    gonic
    -0.54
    tières
    -0.54
     cuantos
    -0.53
     pescoço
    -0.53
    
    -0.52
     DBNull
    -0.52
    dyn
    -0.51
     Roskov
    -0.51
    SourceChecksum
    -0.50
    POSITIVE LOGITS
     exactly
    2.33
    exactly
    2.03
     Exactly
    1.88
    Exactly
    1.75
     EXACTLY
    1.57
     exactement
    1.51
     exatamente
    1.49
     exactamente
    1.48
     precisely
    1.40
     esattamente
    1.34
    Activations Density 3.990%

    No Known Activations