© 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. 5194
    Prev
    Next
    INDEX
    Explanations

    mentions of reasons for things and their justification

    oai_token-act-pair · gemini-2.0-flash

    reason

    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
     acceptez
    -0.40
     اطلع
    -0.40
     Fiche
    -0.40
     pove
    -0.36
     Abonnez
    -0.35
     Beweis
    -0.35
     bbox
    -0.35
    guien
    -0.34
     definiciones
    -0.34
     siguran
    -0.34
    POSITIVE LOGITS
    StructEnd
    0.85
    tanleria
    0.82
    ThroughAttribute
    0.81
    PerformLayout
    0.80
    UpInside
    0.69
    AnchorTagHelper
    0.69
    ništ
    0.66
    levance
    0.66
    bcryptjs
    0.66
    >{@
    0.64
    Activations Density 11.202%

    No Known Activations