© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16238
    Prev
    Next
    INDEX
    Explanations

    words related to reliability and faith

    oai_token-act-pair · gemini-2.0-flash

    programming errors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     trust
    -2.86
     Trust
    -2.75
    Trust
    -2.69
     TRUST
    -2.59
    trust
    -2.56
     trusts
    -2.53
    TRUST
    -2.41
     trusted
    -2.38
     trusting
    -2.33
     Trusts
    -2.28
    POSITIVE LOGITS
    enderror
    0.74
     MenuView
    0.63
    InjectAttribute
    0.60
     دیکھیے
    0.57
    baric
    0.54
    onedDateTime
    0.54
    Vidite
    0.54
    ագրություններ
    0.54
     ModelExpression
    0.53
    FXML
    0.52
    Activations Density 2.910%

    No Known Activations