© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1080
    Prev
    Next
    INDEX
    Explanations

    java code

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Final
    -0.50
    final
    -0.47
    u
    -0.46
    ens
    -0.46
    esch
    -0.44
     acta
    -0.44
    GEBURTSDATUM
    -0.44
    MUM
    -0.42
     العنوان
    -0.42
    os
    -0.41
    POSITIVE LOGITS
     CreateTagHelper
    0.90
    BeginContext
    0.75
    featureID
    0.65
     تضيفلها
    0.62
    azgo
    0.59
    SafeMath
    0.59
     parseFrom
    0.59
    AddHtmlAttribute
    0.59
     كومونز
    0.58
    findpost
    0.58
    Activations Density 1.450%

    No Known Activations