© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15029
    Prev
    Next
    INDEX
    Explanations

    uses of the word "you" and related words/phrases, especially when used to address the reader.

    oai_token-act-pair · gemini-2.0-flash

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     $
    -0.44
    ляю
    -0.44
    son
    -0.42
     <
    -0.41
     Sch
    -0.40
    era
    -0.39
    تعداد
    -0.38
     G
    -0.38
     
    -0.38
    toJson
    -0.36
    POSITIVE LOGITS
    rungsseite
    1.33
     tartalomajánló
    1.11
    findpost
    1.10
    IntoConstraints
    1.02
    enumii
    1.01
    +#+#
    1.01
    mybatisplus
    0.99
    VersionUID
    0.96
    GEBURTSDATUM
    0.93
    Espèce
    0.92
    Activations Density 0.419%

    No Known Activations