Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12072
    Prev
    Next
    INDEX
    Explanations

    the letter 'r', and possibly the string "CTR"

    oai_token-act-pair · gemini-2.0-flash

    R/r

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    ⓧ
    -0.92
    MemoryWarning
    -0.91
    AddTagHelper
    -0.88
     AttributeSet
    -0.80
     Chwiliwch
    -0.79
     يتيمه
    -0.78
    providedIn
    -0.78
     BoxFit
    -0.78
    脚注の使い方
    -0.78
    InputBorder
    -0.77
    POSITIVE LOGITS
    <bos>
    0.40
    fe
    0.35
    ator
    0.35
    st
    0.34
    legt
    0.33
    ona
    0.32
    py
    0.32
    ui
    0.32
    aita
    0.31
    ones
    0.31
    Activations Density 8.949%

    No Known Activations