© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8384
    Prev
    Next
    INDEX
    Explanations

    what the author is doing, reading, or writing, or what they think is good.

    oai_token-act-pair · gemini-2.0-flash

    Legal/formal language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Roskov
    -1.02
     дописавши
    -0.99
     nahilalakip
    -0.96
     lenker
    -0.93
    ThroughAttribute
    -0.90
     فريبيس
    -0.87
     kaynağından
    -0.86
     صوتيه
    -0.84
    AddTagHelper
    -0.81
     EconPapers
    -0.81
    POSITIVE LOGITS
     hereinafter
    0.63
     hereby
    0.58
     further
    0.52
     herein
    0.50
     annum
    0.48
     aesthetically
    0.46
     partake
    0.45
    mektedir
    0.45
     subsequently
    0.44
     esteemed
    0.43
    Activations Density 7.457%

    No Known Activations