© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14694
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement through a location.

    oai_token-act-pair · gemini-2.0-flash

    Travel, direction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Efq
    -1.08
     myſelf
    -1.06
     itſelf
    -1.05
     ſtate
    -1.03
     Conſ
    -1.02
     Theſe
    -1.02
     whoſe
    -1.02
     Jefus
    -1.00
    ſelf
    -1.00
     Diſ
    -0.99
    POSITIVE LOGITS
     "
    0.52
     rien
    0.46
     O
    0.46
     
    0.46
     /
    0.46
     trial
    0.45
    inephrine
    0.45
    ↵↵
    0.45
     (
    0.45
     la
    0.45
    Activations Density 4.273%

    No Known Activations