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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7205
    Prev
    Next
    INDEX
    Explanations

    the word "unless" and words that are sometimes capitalized

    oai_token-act-pair · gemini-2.0-flash

    unless

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     V
    -0.67
     «
    -0.65
     Me
    -0.65
     (
    -0.64
    inc
    -0.64
     Mar
    -0.62
     Di
    -0.62
    ,
    -0.62
     Mor
    -0.61
    <eos>
    -0.60
    POSITIVE LOGITS
    <bos>
    1.35
     photolibrary
    1.35
     myſelf
    1.33
     itſelf
    1.32
     doubtnut
    1.26
     quæ
    1.23
     Efq
    1.22
     ſind
    1.21
     purpoſe
    1.19
     Monfieur
    1.19
    Activations Density 0.889%

    No Known Activations