© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12310
    Prev
    Next
    INDEX
    Explanations

    words related to walking or hiking

    oai_token-act-pair · gemini-2.0-flash

    the word 'through'

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    InstanceState
    -0.62
     FetchType
    -0.52
     salonu
    -0.51
    Wired
    -0.48
    ólica
    -0.45
    OrCreate
    -0.45
    Forte
    -0.45
     iniqu
    -0.45
    car
    -0.45
    อล
    -0.44
    POSITIVE LOGITS
     through
    1.15
    through
    0.96
     past
    0.96
    Through
    0.96
     Through
    0.93
     THROUGH
    0.93
     attraverso
    0.91
    THROUGH
    0.86
     thru
    0.84
     través
    0.79
    Activations Density 2.002%

    No Known Activations