© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6024
    Prev
    Next
    INDEX
    Explanations

    language about stopping something repeatedly

    oai_token-act-pair · gemini-2.0-flash

    stop

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    GEBURTSDATUM
    -0.72
    KommentareTeilen
    -0.66
     Euphrates
    -0.60
    .*")]
    -0.59
    extAlignment
    -0.59
     hefyd
    -0.58
     Schur
    -0.55
     Signalez
    -0.55
     صوتيه
    -0.55
    enumii
    -0.54
    POSITIVE LOGITS
     best
    0.46
     Vater
    0.46
     drive
    0.46
    фия
    0.45
     towards
    0.43
     drove
    0.43
     miej
    0.43
    AccessorTable
    0.43
    Exports
    0.42
    Values
    0.42
    Activations Density 15.591%

    No Known Activations