© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10780
    Prev
    Next
    INDEX
    Explanations

    terms related to neural networks or ornithology/bird hunting

    oai_token-act-pair · gemini-2.0-flash

    living things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     ſeveral
    -0.61
    HostException
    -0.59
     myſelf
    -0.57
    ſelf
    -0.54
     ModelAndView
    -0.52
    AdapterFactory
    -0.51
     pinulongan
    -0.51
     Michaelis
    -0.51
     Monfieur
    -0.50
     moſt
    -0.50
    POSITIVE LOGITS
     Normdatei
    0.67
    AddTagHelper
    0.56
     recognition
    0.56
    ArgsConstructor
    0.55
     Roskov
    0.54
     detection
    0.54
    recognition
    0.54
     detector
    0.54
     Detectors
    0.53
     DETECTION
    0.52
    Activations Density 1.317%

    No Known Activations