© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3596
    Prev
    Next
    INDEX
    Explanations

    directional words in relation to geographical locations

    oai_token-act-pair · gemini-2.0-flash

    directions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     left
    -1.45
    Left
    -1.35
     Left
    -1.27
    left
    -1.19
     LEFT
    -1.16
    LEFT
    -1.05
    Right
    -1.04
     Right
    -1.02
    right
    -1.00
     right
    -1.00
    POSITIVE LOGITS
    TypedDataSet
    0.69
    ChildScrollView
    0.66
    AndEndTag
    0.65
    Diweddarwch
    0.60
    älde
    0.60
     mouseY
    0.59
    strahlung
    0.56
    EndContext
    0.52
    OGND
    0.51
    +#+
    0.50
    Activations Density 0.361%

    No Known Activations