© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13417
    Prev
    Next
    INDEX
    Explanations

    words related to initiating a project or organization

    oai_token-act-pair · gemini-2.0-flash

    Establishing/founding

    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
     <<<<<<<<<<<<<<
    -0.68
     Wiktionnaire
    -0.60
    enumi
    -0.58
     BoxDecoration
    -0.55
     radon
    -0.54
     مشين
    -0.53
     Ptolemy
    -0.53
    enumii
    -0.51
     Sandman
    -0.50
    󠁢
    -0.50
    POSITIVE LOGITS
     rich
    0.54
     Rich
    0.54
    accepte
    0.53
     a
    0.53
    Rich
    0.52
    rich
    0.52
     artikkelen
    0.51
     følgende
    0.48
    είο
    0.48
    onsored
    0.47
    Activations Density 0.498%

    No Known Activations