© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 495
    Prev
    Next
    INDEX
    Explanations

    legal arguments about the court not addressing an issue

    oai_token-act-pair · gemini-2.0-flash

    legal attempts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ConstraintMaker
    -0.51
    oredCriteria
    -0.51
    Rhestr
    -0.47
     condition
    -0.47
    Condition
    -0.45
    condition
    -0.45
    TE
    -0.44
    witt
    -0.43
    zesi
    -0.43
     conditioned
    -0.42
    POSITIVE LOGITS
    FieldBuilder
    0.66
    angliski
    0.63
     néglig
    0.60
    URLException
    0.58
    smöglichkeiten
    0.53
    bbene
    0.53
    enumi
    0.52
    pholes
    0.52
     '\''
    0.52
     InputDecoration
    0.52
    Activations Density 3.303%

    No Known Activations