© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3510
    Prev
    Next
    INDEX
    Explanations

    roads, trails, and routes, frequently finding the word "trail" itself

    oai_token-act-pair · gemini-2.0-flash

    Roads and trails

    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
    ScopeManager
    -0.79
     Lead
    -0.55
    ठा
    -0.55
    jen
    -0.53
     lead
    -0.52
    esModule
    -0.52
     Réponses
    -0.51
    Lead
    -0.50
    脚注の使い方
    -0.50
    extAlignment
    -0.50
    POSITIVE LOGITS
     referenties
    0.56
    kháu
    0.55
    bed
    0.53
    はじめに
    0.50
     piacere
    0.49
    beds
    0.48
    InBackground
    0.48
    Spoljašnje
    0.48
    culously
    0.47
    KommentareTeilen
    0.47
    Activations Density 12.867%

    No Known Activations