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. 12117
    Prev
    Next
    INDEX
    Explanations

    German text with modal verbs, especially the word "man" and related sentence structure.

    oai_token-act-pair · gemini-2.0-flash

    German text

    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
    and
    -0.43
     us
    -0.41
    -
    -0.38
     n
    -0.37
    us
    -0.37
    pi
    -0.37
    g
    -0.37
    :
    -0.37
    fa
    -0.36
    item
    -0.36
    POSITIVE LOGITS
     Monfieur
    1.41
     myſelf
    1.34
     Jefus
    1.27
     ſeveral
    1.23
     Eſ
    1.22
     Theſe
    1.21
     itſelf
    1.20
     Majefty
    1.18
     $_"
    1.18
    tagHelperRunner
    1.18
    Activations Density 0.328%

    No Known Activations