© 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. 6467
    Prev
    Next
    INDEX
    Explanations

    words related to legal jargon and references

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    ce
    -0.48
    j
    -0.47
      
    -0.46
    O
    -0.43
    &
    -0.42
    z
    -0.42
    +
    -0.42
    ↵
    -0.42
    to
    -0.41
     flori
    -0.41
    POSITIVE LOGITS
     tartalomajánló
    1.19
    Hentet
    1.15
     disambiguazione
    1.03
    المناصب
    0.98
    tagHelperRunner
    0.98
    enumi
    0.98
    Personensuche
    0.95
    XmlAccessType
    0.94
     esternos
    0.91
    Datuak
    0.91
    Activations Density 2.727%

    No Known Activations