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. 12021
    Prev
    Next
    INDEX
    Explanations

    French text, possibly with some conversational tone, including common words and accents.

    oai_token-act-pair · gemini-2.0-flash

    de

    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
     pleaſure
    -1.24
     purpoſe
    -1.13
     itſelf
    -1.08
     myſelf
    -1.07
     houſe
    -1.07
     poffe
    -1.02
     Majefty
    -1.02
     fubject
    -1.01
     greateſt
    -1.00
     ſtate
    -0.99
    POSITIVE LOGITS
     la
    0.80
     l
    0.75
     lo
    0.45
     los
    0.44
     te
    0.36
     ces
    0.33
     nos
    0.32
    Šaltiniai
    0.32
     chacun
    0.31
     las
    0.31
    Activations Density 0.475%

    No Known Activations