© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2722
    Prev
    Next
    INDEX
    Explanations

    validation around user input, arguments, or code functionality

    oai_token-act-pair · gemini-2.0-flash

    validation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.69
    OptionsMenu
    -0.63
    jupiter
    -0.54
    Kanpo
    -0.53
     Réponses
    -0.52
    modelBuilder
    -0.52
    󠁢
    -0.49
    ErrUnexpectedEOF
    -0.48
     ibland
    -0.47
    ituaries
    -0.46
    POSITIVE LOGITS
     valid
    0.70
    WebElementEntity
    0.67
    valid
    0.65
     valide
    0.59
     مُعرِّف
    0.56
     CanadaChoose
    0.56
     invalid
    0.55
    bcryptjs
    0.52
     VALID
    0.52
    ecake
    0.52
    Activations Density 2.221%

    No Known Activations