© 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. 9568
    Prev
    Next
    INDEX
    Explanations

    descriptions of buildings and their locations within a multi-level structure

    oai_token-act-pair · gemini-2.0-flash

    locations of things

    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
     auffi
    -0.73
     purpoſe
    -0.73
     himſelf
    -0.71
     myſelf
    -0.71
     iſt
    -0.68
     ſtate
    -0.67
    elemField
    -0.66
    <?,
    -0.65
     ſch
    -0.63
    glEnd
    -0.63
    POSITIVE LOGITS
    ⓧ
    0.52
    AddHtmlAttribute
    0.49
    ьаж
    0.48
     faudrait
    0.46
     fallait
    0.46
    次
    0.44
    Rüyada
    0.43
    раздо
    0.43
     T
    0.42
    tice
    0.42
    Activations Density 4.494%

    No Known Activations