© 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. 3747
    Prev
    Next
    INDEX
    Explanations

    words and prepositions that often appear with verbs expressing anticipation or desire

    oai_token-act-pair · gemini-2.0-flash

    blog post excerpts

    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
    I
    -0.50
    -
    -0.49
    S
    -0.47
    ,
    -0.47
    th
    -0.45
    (
    -0.44
    .
    -0.44
     
    -0.43
    tr
    -0.43
    D
    -0.41
    POSITIVE LOGITS
    setVerticalGroup
    1.13
    styleType
    1.13
    出版年
    1.12
     Normdatei
    1.10
     myſelf
    1.08
    LabelTagHelper
    1.07
     purpoſe
    1.05
    oredCriteria
    1.04
     gaining
    1.04
     proving
    1.03
    Activations Density 4.932%

    No Known Activations