© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    words related to outdoor trails

    oai_token-act-pair · gemini-2.0-flash

    Trail descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     teuer
    -0.47
     pertes
    -0.45
    per
    -0.44
    InternalFrame
    -0.43
     محفوظة
    -0.42
    Varint
    -0.42
    ্ন
    -0.42
    pes
    -0.41
    requireNonNull
    -0.41
    ciutto
    -0.41
    POSITIVE LOGITS
    tonsoft
    0.83
     EconPapers
    0.79
     continúas
    0.77
     Signalez
    0.73
    NameInMap
    0.70
    ագրություններ
    0.68
    Билгалдахарш
    0.66
     CreateTagHelper
    0.65
    <?
    0.65
    Gemeinden
    0.62
    Activations Density 0.630%

    No Known Activations