© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    grammatically unsound text

    oai_token-act-pair · gemini-2.0-flash

    forcibly

    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
     EconPapers
    -0.84
     propOrder
    -0.82
     Савезне
    -0.80
    المشاركات
    -0.80
     AssemblyCulture
    -0.79
     Poznań
    -0.71
    windowFixed
    -0.71
    NUMX
    -0.70
    resave
    -0.70
    addCriterion
    -0.69
    POSITIVE LOGITS
     threw
    0.44
    licon
    0.43
    ca
    0.42
    hami
    0.38
     grosso
    0.38
    Жа
    0.37
     Reconnaissance
    0.37
     cond
    0.37
    átu
    0.36
    ed
    0.35
    Activations Density 1.052%

    No Known Activations