© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    words related to taking action or recording steps in an action

    oai_token-act-pair · gemini-2.0-flash

    Taking action/legal matters

    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
     action
    -3.06
     Action
    -3.03
    Action
    -2.95
     ACTION
    -2.88
     Actions
    -2.86
    action
    -2.81
    ACTION
    -2.72
     actions
    -2.67
    Actions
    -2.66
    actions
    -2.64
    POSITIVE LOGITS
    zunehmen
    0.50
    Hentet
    0.49
    vaila
    0.49
     mines
    0.48
    sse
    0.45
    íses
    0.45
     맞
    0.44
    خد
    0.44
    PARATUS
    0.44
    oraus
    0.43
    Activations Density 2.276%

    No Known Activations