© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12537
    Prev
    Next
    INDEX
    Explanations

    lines of code containing parameter names and values in a hierarchical format, especially those related to hardware configurations and statistics

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    IntoConstraints
    -1.22
     myſelf
    -1.20
    ^(@)
    -1.20
     EconPapers
    -1.14
     itſelf
    -1.13
     doubtnut
    -1.11
    MigrationBuilder
    -1.11
     themſelves
    -1.10
     CreateTagHelper
    -1.07
    wiſe
    -1.06
    POSITIVE LOGITS
    ↵↵
    0.66
    <eos>
    0.52
    ↵
    0.43
    ‍
    0.41
    R
    0.41
    </strong>
    0.40
    ...
    0.40
     ,
    0.40
    .
    0.39
    L
    0.39
    Activations Density 5.821%

    No Known Activations