© 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. 12587
    Prev
    Next
    INDEX
    Explanations

    phrases that relate to the concept of moving from one thing to another, either physically or figuratively.

    oai_token-act-pair · gemini-2.0-flash

    move

    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
    tagHelper
    -0.72
     ErrIntOverflow
    -0.70
    WebServlet
    -0.65
     kasarigan
    -0.64
     AssemblyCompany
    -0.63
     חיצוניים
    -0.62
    mbic
    -0.61
    PageRoute
    -0.60
    refour
    -0.59
    AddRef
    -0.57
    POSITIVE LOGITS
     tartalomajánló
    0.52
     NM
    0.49
    Rohy
    0.45
     DMG
    0.44
     guards
    0.44
    geom
    0.43
     zvuky
    0.40
    JNIEnv
    0.40
    ingtones
    0.40
     towns
    0.40
    Activations Density 22.211%

    No Known Activations