© 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. 13188
    Prev
    Next
    INDEX
    Explanations

    the word "blow" or words related to that action

    oai_token-act-pair · gemini-2.0-flash

    blow

    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
     blow
    -2.23
     blows
    -1.92
     blowing
    -1.92
     blown
    -1.91
    blow
    -1.90
     blew
    -1.87
     Blow
    -1.86
    Blow
    -1.82
    blowing
    -1.65
    blown
    -1.46
    POSITIVE LOGITS
     RequestMethod
    0.51
    telemetry
    0.47
     bullion
    0.47
    tumblr
    0.45
    Principales
    0.45
    collier
    0.45
     muñeca
    0.44
    TagHelpers
    0.44
    dziew
    0.44
    InstanceState
    0.44
    Activations Density 6.461%

    No Known Activations