© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6783
    Prev
    Next
    INDEX
    Explanations

    locations in Scotland

    oai_token-act-pair · gemini-2.0-flash

    Scottish places and politics

    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
    TableHead
    -0.55
    /*
    -0.53
    Handlung
    -0.50
     viewDidLoad
    -0.49
    PMailer
    -0.49
    enderror
    -0.48
    /**
    -0.47
    stdc
    -0.47
    pstead
    -0.47
    onAttach
    -0.47
    POSITIVE LOGITS
    IndentedString
    0.68
    +#+#
    0.67
     Alonzo
    0.63
     ergonomics
    0.61
     ASR
    0.54
     AIAA
    0.54
     Whig
    0.53
     Majefty
    0.52
    CharField
    0.52
     Poles
    0.52
    Activations Density 1.005%

    No Known Activations