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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9972
    Prev
    Next
    INDEX
    Explanations

    hyperlinks, references, and categories related to biographical data

    oai_token-act-pair · gemini-2.0-flash

    links/references

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Paglinawan
    -0.77
    Scénario
    -0.65
    IBAction
    -0.65
    aarrggbb
    -0.60
     ब्रेकडाउन
    -0.59
    openConnection
    -0.57
    ">+
    -0.57
    Abitanti
    -0.56
    ---*/
    -0.55
    Introduced
    -0.55
    POSITIVE LOGITS
     cherchés
    0.52
     ràng
    0.47
    хьтан
    0.41
    Personendaten
    0.41
     Planet
    0.41
    ffin
    0.41
    Planet
    0.40
     project
    0.40
    gerufen
    0.40
    mployment
    0.39
    Activations Density 1.122%

    No Known Activations