© 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. 12817
    Prev
    Next
    INDEX
    Explanations

    references to cardinal directions or buildings.

    oai_token-act-pair · gemini-2.0-flash

    wall, northern

    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
    出版年
    -0.73
    <bos>
    -0.66
    tagext
    -0.63
    BASEPATH
    -0.56
    DockStyle
    -0.54
    +#+
    -0.53
    ั่น
    -0.53
    });*/
    -0.52
     pfalz
    -0.52
    Identyfik
    -0.51
    POSITIVE LOGITS
    /**
    0.52
    SequentialGroup
    0.50
    cellaneous
    0.48
    ObjectModel
    0.47
    GraphicsUnit
    0.46
    endants
    0.46
     tan
    0.46
    tainable
    0.45
    kward
    0.45
     horizontally
    0.45
    Activations Density 4.653%

    No Known Activations