© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10762
    Prev
    Next
    INDEX
    Explanations

    sentence fragments, numbers, and some words like "versus" and "tics" perhaps in a medical context

    oai_token-act-pair · gemini-2.0-flash

    programming or coding constructs

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Identyfik
    -0.51
    ):}
    -0.51
     ''
    -0.48
    ],\
    -0.47
    ],
    -0.47
    ęku
    -0.46
    ſelf
    -0.45
    pointed
    -0.45
     }}-
    -0.44
     '',
    -0.44
    POSITIVE LOGITS
     []:
    0.66
     <<<<<<<<<<<<<<
    0.64
    openSession
    0.63
    MetaObject
    0.62
    AtIndexPath
    0.61
     NSCoder
    0.61
     cref
    0.60
    PhysRevLett
    0.57
     BioLib
    0.57
    StoryboardSegue
    0.57
    Activations Density 4.029%

    No Known Activations