© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 353
    Prev
    Next
    INDEX
    Explanations

    fragments of words ending in "as", "Set","Past", "tran","Ros", "Brus","Par", "Re",or related to diagrams.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lenker
    -0.71
    bkz
    -0.70
    s
    -0.65
     ControllerBase
    -0.65
    InitVars
    -0.65
    encodeWith
    -0.64
     LoggerFactory
    -0.64
    RTDA
    -0.64
    CreateModel
    -0.63
     MainAxisSize
    -0.63
    POSITIVE LOGITS
    he
    0.60
    hen
    0.56
    teen
    0.51
    how
    0.49
    hes
    0.49
    sik
    0.48
    hew
    0.48
    hap
    0.48
    hev
    0.47
    haga
    0.47
    Activations Density 2.379%

    No Known Activations