© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11169
    Prev
    Next
    INDEX
    Explanations

    the word "through" or its variations

    oai_token-act-pair · gemini-2.0-flash

    through

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     through
    -1.80
    through
    -1.66
    Through
    -1.64
     Through
    -1.54
     THROUGH
    -1.48
     attraverso
    -1.45
     través
    -1.43
     através
    -1.38
    THROUGH
    -1.30
     melalui
    -1.29
    POSITIVE LOGITS
     dere
    0.58
    GPP
    0.51
    nante
    0.49
    ScopeManager
    0.47
    heber
    0.47
     Dere
    0.46
    habhar
    0.46
    itchfield
    0.46
    solete
    0.44
    GLAS
    0.44
    Activations Density 0.399%

    No Known Activations