© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12815
    Prev
    Next
    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gemini-2.0-flash

    phrases indicating past experiences or actions

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

    had

    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
     had
    -1.96
    Had
    -1.93
     Had
    -1.84
    had
    -1.74
     HAD
    -1.51
     hadden
    -1.43
     hadde
    -1.38
    HAD
    -1.32
     hatte
    -1.31
     hatten
    -1.30
    POSITIVE LOGITS
     just
    0.56
     terk
    0.45
    just
    0.44
    itake
    0.41
    enterOuterAlt
    0.40
    transQ
    0.40
     Teg
    0.39
     Sabina
    0.39
    ชน
    0.39
     once
    0.38
    Activations Density 1.172%

    No Known Activations