© 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. 15732
    Prev
    Next
    INDEX
    Explanations

    sentences describing that something exists or has happened

    oai_token-act-pair · gemini-2.0-flash

    mention of 'long' duration

    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
     hObject
    -0.54
    Билгалдахарш
    -0.50
    Previously
    -0.47
     próprios
    -0.47
     Previously
    -0.46
    meist
    -0.46
     semula
    -0.46
     CreateTagHelper
    -0.46
    Tä
    -0.44
     Lightboxes
    -0.44
    POSITIVE LOGITS
     long
    2.75
    long
    2.36
     LONG
    1.83
    Long
    1.80
     Long
    1.79
    LONG
    1.60
     longue
    1.51
     longa
    1.42
     longterm
    1.38
     longs
    1.34
    Activations Density 7.456%

    No Known Activations