© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13232
    Prev
    Next
    INDEX
    Explanations

    the verb "say" or its variants

    oai_token-act-pair · gemini-2.0-flash

    say

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     say
    -1.52
    say
    -1.41
    Say
    -1.31
     Say
    -1.14
     SAY
    -1.05
    ReusableCell
    -1.02
    mybatisplus
    -0.98
    например
    -0.97
     např
    -0.94
    UnsafeEnabled
    -0.94
    POSITIVE LOGITS
     and
    0.71
    ↵↵
    0.62
     are
    0.56
    -
    0.55
     he
    0.54
    '
    0.54
    .
    0.54
    ’
    0.52
     how
    0.52
     offers
    0.51
    Activations Density 0.183%

    No Known Activations