© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13086
    Prev
    Next
    INDEX
    Explanations

    names

    oai_token-act-pair · gemini-2.0-flash

    acronyms and names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -0.81
     незавершена
    -0.69
     ComVisible
    -0.66
    цездатний
    -0.60
     Shakspeare
    -0.59
     Normdatei
    -0.56
     Hera
    -0.56
     '\\;'
    -0.55
    र्शन
    -0.55
    ToEnd
    -0.55
    POSITIVE LOGITS
     Lup
    0.61
     leksikon
    0.60
    Parcelize
    0.59
    olus
    0.55
    mcc
    0.55
     Rugg
    0.54
    lacian
    0.54
    tag
    0.53
     McC
    0.52
     Vign
    0.51
    Activations Density 0.518%

    No Known Activations