© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12083
    Prev
    Next
    INDEX
    Explanations

    the word "facts", sometimes in combination with other words that indicate a need to know or find out information

    oai_token-act-pair · gemini-2.0-flash

    facts

    np_max-act · gemini-2.0-flash

    facts

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     –
    -0.62
    s
    -0.57
     users
    -0.56
    orges
    -0.52
     soon
    -0.52
    iyle
    -0.52
      
    -0.51
     clients
    -0.50
    freies
    -0.49
     The
    -0.49
    POSITIVE LOGITS
    findpost
    1.20
    AsUp
    0.93
     Roskov
    0.89
    ftagPool
    0.88
     Chwiliwch
    0.87
    CPtr
    0.85
    LookAnd
    0.84
     Meksiku
    0.83
    mybatisplus
    0.82
    ########.
    0.81
    Activations Density 1.651%

    No Known Activations