© 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. 5899
    Prev
    Next
    INDEX
    Explanations

    passages that describe how something is being made available for someone to use

    oai_token-act-pair · gemini-2.0-flash

    allowing, allow, allows

    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
    OOT
    -0.65
    ccoli
    -0.60
     CascadeType
    -0.58
    ografija
    -0.55
    estinations
    -0.55
    InSection
    -0.54
     createSprite
    -0.54
    irmer
    -0.54
    chafts
    -0.53
    triques
    -0.52
    POSITIVE LOGITS
     allowing
    1.49
     allow
    1.46
     allows
    1.35
     enabling
    1.34
    allowing
    1.23
     enable
    1.23
     Allowing
    1.23
    allow
    1.20
    Allow
    1.20
     enables
    1.20
    Activations Density 2.406%

    No Known Activations