© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3817
    Prev
    Next
    INDEX
    Explanations

    locations (cities, states, regions) and words associated with geography

    oai_token-act-pair · gemini-2.0-flash

    geographic locations and names

    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
    webElementXpaths
    -0.61
     south
    -0.61
     South
    -0.60
     Süd
    -0.59
    South
    -0.59
    SOUTH
    -0.56
     SOUTH
    -0.56
    south
    -0.56
     North
    -0.55
     Western
    -0.55
    POSITIVE LOGITS
    脚注の使い方
    0.76
    orianCalendar
    0.55
     ModelExpression
    0.55
     endforeach
    0.54
    ]));
    0.54
    mány
    0.53
    Browsable
    0.51
    ")));
    0.50
    #+#
    0.49
     mouseClicked
    0.48
    Activations Density 1.060%

    No Known Activations