© 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. 13577
    Prev
    Next
    INDEX
    Explanations

    a technical document with numbers and codes or mathematical formulas and network terminology or statistical analysis results

    oai_token-act-pair · gemini-2.0-flash

    2

    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
    Personendaten
    -1.12
     resourceCulture
    -1.02
    MessageTagHelper
    -1.00
     typelib
    -0.99
    Personensuche
    -0.91
     Signalez
    -0.91
    WriteBarrier
    -0.90
    LookAnd
    -0.90
    AndroidJUnit
    -0.89
     '\\;'
    -0.88
    POSITIVE LOGITS
    nd
    0.65
    st
    0.38
    nder
    0.36
     Viter
    0.35
    9
    0.34
    furt
    0.33
    sha
    0.33
    ns
    0.33
    ka
    0.33
    ND
    0.33
    Activations Density 7.058%

    No Known Activations