© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7905
    Prev
    Next
    INDEX
    Explanations

    the word "route," referencing paths, directions, or means of transportation

    oai_token-act-pair · gemini-2.0-flash

    route

    np_max-act · gemini-2.0-flash
    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
     De
    -0.75
     Ga
    -0.74
     Fe
    -0.71
     M
    -0.71
     cre
    -0.69
     so
    -0.69
     my
    -0.68
     L
    -0.68
     she
    -0.68
     Le
    -0.68
    POSITIVE LOGITS
     Houſe
    1.40
     houſe
    1.40
     Reſ
    1.38
     Jefus
    1.30
     Shakspeare
    1.29
     étoit
    1.29
     Monfieur
    1.29
     themſelves
    1.27
     feroit
    1.27
     avoient
    1.26
    Activations Density 2.255%

    No Known Activations