© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15827
    Prev
    Next
    INDEX
    Explanations

    the word "surface"

    oai_token-act-pair · gemini-2.0-flash

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     piece
    -0.58
    ↵↵
    -0.58
    ה
    -0.55
     section
    -0.53
    <bos>
    -0.52
     construction
    -0.52
    deaux
    -0.52
     〈
    -0.52
    Section
    -0.51
     juda
    -0.49
    POSITIVE LOGITS
    +#+#
    1.16
     Roskov
    1.14
     resourceCulture
    1.07
    IsContent
    0.99
    AutoScale
    0.98
    UnusedPrivate
    0.96
     EconPapers
    0.94
     مرئيه
    0.94
     kasarigan
    0.89
     nakalista
    0.87
    Activations Density 1.290%

    No Known Activations