© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10917
    Prev
    Next
    INDEX
    Explanations

    econometric publications and authors

    oai_token-act-pair · gemini-2.0-flash

    academic citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Normdatei
    -0.86
    RectangleBorder
    -0.84
    UnknownFields
    -0.80
    发表于
    -0.78
    ChildScrollView
    -0.77
    Portale
    -0.77
    ſelves
    -0.71
     ་་
    -0.71
     AssemblyCulture
    -0.70
    AndEndTag
    -0.69
    POSITIVE LOGITS
     poches
    0.54
     trov
    0.54
     fraî
    0.53
     piede
    0.50
     cucchia
    0.50
     titolata
    0.50
     preparazione
    0.50
     puissante
    0.50
     Esti
    0.49
     polvere
    0.49
    Activations Density 20.049%

    No Known Activations