© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12284
    Prev
    Next
    INDEX
    Explanations

    html code, especially language and URL specifications

    oai_token-act-pair · gemini-2.0-flash

    languages

    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
     $__
    -0.42
     vilá
    -0.39
    او
    -0.38
    ate
    -0.36
    >
    -0.35
     tvar
    -0.35
    vature
    -0.35
    ιβ
    -0.35
    IContainer
    -0.34
    eraus
    -0.34
    POSITIVE LOGITS
     English
    2.64
    English
    2.30
     english
    2.22
     ENGLISH
    2.08
     Spanish
    1.93
    english
    1.83
    ENGLISH
    1.72
    Spanish
    1.68
     French
    1.65
     Portuguese
    1.59
    Activations Density 6.375%

    No Known Activations