© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3071
    Prev
    Next
    INDEX
    Explanations

    words related to navigation or directions like right, left, way, vessel, crossing, around, etc

    oai_token-act-pair · gemini-2.0-flash

    port or turn

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    xase
    -0.75
     CreateTagHelper
    -0.74
    Filmografie
    -0.71
     الحره
    -0.70
    InstanceState
    -0.64
     Efq
    -0.63
     contextLoads
    -0.63
     */;
    -0.63
     billig
    -0.63
     Pingback
    -0.62
    POSITIVE LOGITS
     port
    0.71
    port
    0.60
    Port
    0.59
     Port
    0.58
    PORT
    0.57
     turn
    0.55
     PORT
    0.49
     turning
    0.48
    turn
    0.46
     turns
    0.45
    Activations Density 2.413%

    No Known Activations