© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3763
    Prev
    Next
    INDEX
    Explanations

    financial transactions involving goods and materials

    oai_token-act-pair · gemini-2.0-flash

    good

    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
    twimg
    -0.69
    moveToNext
    -0.57
    contentLoaded
    -0.57
    quets
    -0.52
    äiv
    -0.50
    qtype
    -0.49
    WriteAttribute
    -0.49
    cheibe
    -0.49
    izawa
    -0.47
    ########.
    -0.47
    POSITIVE LOGITS
     good
    2.28
    good
    2.16
    Good
    2.06
     Good
    2.03
    GOOD
    1.97
     GOOD
    1.86
     gute
    1.22
     buena
    1.17
     buenas
    1.11
     guten
    1.10
    Activations Density 1.549%

    No Known Activations