© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10652
    Prev
    Next
    INDEX
    Explanations

    pronouns such as "I" "they" or "you" along with words related to those pronouns

    oai_token-act-pair · gemini-2.0-flash

    personal references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     what
    -0.52
     trasparente
    -0.48
    Zeneca
    -0.45
     meleg
    -0.44
    enfone
    -0.44
    istock
    -0.44
     buono
    -0.44
     couvrir
    -0.43
    trui
    -0.43
     dál
    -0.42
    POSITIVE LOGITS
    المناصب
    0.78
    httphttps
    0.68
     فريبيس
    0.66
    Datuak
    0.65
    )':
    0.64
     Chwiliwch
    0.63
    AddTagHelper
    0.62
    MIDDLEWARE
    0.60
     HasFactory
    0.60
     tartalomajánló
    0.60
    Activations Density 9.780%

    No Known Activations