© 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. 3282
    Prev
    Next
    INDEX
    Explanations

    descriptions of real estate properties, including things like number of bathrooms and bedrooms

    oai_token-act-pair · gemini-2.0-flash

    Housing/rooms

    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
     Paglinawan
    -0.87
     purpoſe
    -0.76
     Muses
    -0.70
     Theſe
    -0.70
     themſelves
    -0.69
     itſelf
    -0.68
     Reſ
    -0.68
    ArrowToggle
    -0.68
     uſed
    -0.67
     himſelf
    -0.66
    POSITIVE LOGITS
     TestBed
    0.59
    spar
    0.56
    WriteBarrier
    0.54
    SizeF
    0.54
     m
    0.49
    httphttps
    0.49
     har
    0.47
     ");
    0.47
     ag
    0.46
    ');
    0.46
    Activations Density 0.835%

    No Known Activations