© 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. 5635
    Prev
    Next
    INDEX
    Explanations

    phrases involving the passage of time and waiting for things to happen

    oai_token-act-pair · gemini-2.0-flash

    wait

    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
     of
    -0.52
    InputBorder
    -0.52
     dourada
    -0.48
    ীর
    -0.47
    winston
    -0.47
    ovanie
    -0.47
     perles
    -0.46
    of
    -0.46
     vierge
    -0.46
     devons
    -0.46
    POSITIVE LOGITS
    脚注の使い方
    0.65
    }{*}{}
    0.58
    atalyst
    0.57
    stateProvider
    0.57
    +#+#
    0.56
    istad
    0.56
    stateMutability
    0.54
    ]--;
    0.54
    atisfaction
    0.52
     defaultstate
    0.52
    Activations Density 20.544%

    No Known Activations