© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15861
    Prev
    Next
    INDEX
    Explanations

    lines of code with errors

    oai_token-act-pair · gemini-2.0-flash

    Code identifiers and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    出版年
    -0.68
    amemnon
    -0.61
     Normdatei
    -0.61
    uarts
    -0.61
    jectures
    -0.60
    -0.59
    phazard
    -0.59
    esgue
    -0.59
    patrón
    -0.58
    AddTagHelper
    -0.57
    POSITIVE LOGITS
    ınt
    0.53
     geste
    0.50
    1
    0.46
    liğini
    0.45
    0
    0.44
     chng
    0.44
    und
    0.44
    ñera
    0.43
     dik
    0.42
    ig
    0.42
    Activations Density 6.442%

    No Known Activations