© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10315
    Prev
    Next
    INDEX
    Explanations

    technical abbreviations and concepts

    oai_token-act-pair · gemini-2.0-flash

    RFI

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    oa̍t
    -0.59
    السكان
    -0.58
    astéro
    -0.56
     Chbosky
    -0.55
    InteropServices
    -0.53
    VersionUID
    -0.52
    shub
    -0.51
    TypeDef
    -0.51
    Tent
    -0.51
    TagHelper
    -0.51
    POSITIVE LOGITS
     تضيفلها
    0.68
    <bos>
    0.56
    InSection
    0.54
     nakalista
    0.53
    fromnode
    0.44
     hefyd
    0.43
    cdnjs
    0.43
    Rhestr
    0.43
     doInBackground
    0.43
     povezave
    0.42
    Activations Density 3.466%

    No Known Activations