© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 642
    Prev
    Next
    INDEX
    Explanations

    the word "in" followed by a reference to a case of some kind

    oai_token-act-pair · gemini-2.0-flash

    say "case"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     situation
    -1.49
     situations
    -1.39
    situation
    -1.32
     Situation
    -1.21
     SITUATION
    -1.20
     Situations
    -1.13
    Situation
    -1.12
     circumstances
    -1.06
     cases
    -1.05
     situação
    -1.05
    POSITIVE LOGITS
    setVerticalGroup
    0.79
    mybatisplus
    0.75
    tagHelperRunner
    0.74
    SequentialGroup
    0.56
    ]--;
    0.56
    opress
    0.55
    Rhestr
    0.54
    .³
    0.53
     hidráulica
    0.53
    %"),
    0.51
    Activations Density 1.014%

    No Known Activations