© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15193
    Prev
    Next
    INDEX
    Explanations

    words related to movement or passage

    oai_token-act-pair · gemini-2.0-flash

    say "through"

    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
    Via
    -1.05
     Via
    -0.97
    via
    -0.84
     via
    -0.82
    VIA
    -0.79
    THROUGH
    -0.68
     VIA
    -0.68
    Through
    -0.61
     thru
    -0.61
     Through
    -0.58
    POSITIVE LOGITS
     th
    0.84
     though
    0.79
    th
    0.76
     threw
    0.74
     throw
    0.74
     TH
    0.71
     Th
    0.70
     thr
    0.69
    Th
    0.69
    Démographie
    0.66
    Activations Density 1.517%

    No Known Activations