© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11804
    Prev
    Next
    INDEX
    Explanations

    words related to city descriptions, especially streets and architecture

    oai_token-act-pair · gemini-2.0-flash

    street

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ISupport
    -0.66
    TagMode
    -0.66
    ">//
    -0.65
    brtc
    -0.57
     Hongrie
    -0.54
    maxcdn
    -0.53
    出版年
    -0.52
    <bos>
    -0.52
    UnsafeEnabled
    -0.52
    hoeddwyd
    -0.51
    POSITIVE LOGITS
     Efq
    0.63
     Wiktionnaire
    0.60
    woordig
    0.56
    Filmographie
    0.54
    CodeAnalysis
    0.52
     district
    0.52
     Majefty
    0.50
    eniendo
    0.50
    atam
    0.49
    olesale
    0.49
    Activations Density 0.931%

    No Known Activations