© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 613
    Prev
    Next
    INDEX
    Explanations

    the formatting and terminology used in academic papers.

    oai_token-act-pair · gemini-2.0-flash

    math publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    +#+#
    -0.63
     offerts
    -0.57
    endphp
    -0.54
    Clik
    -0.52
     présentés
    -0.51
     procede
    -0.49
     oprot
    -0.49
     devenus
    -0.48
     réguli
    -0.48
     bezeichneter
    -0.48
    POSITIVE LOGITS
     normal
    0.59
    det
    0.59
    moduleId
    0.54
     cos
    0.54
     rational
    0.53
     characteristic
    0.53
    DataSetChanged
    0.53
    KURZBESCHREIBUNG
    0.51
     sec
    0.51
    äsident
    0.51
    Activations Density 22.774%

    No Known Activations