© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11539
    Prev
    Next
    INDEX
    Explanations

    phrases indicating doubt, contradiction, or a possible alternative explanation.

    oai_token-act-pair · gemini-2.0-flash

    Allegations and conflicting statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    due
    -0.77
     éprou
    -0.69
     librement
    -0.67
     frequenza
    -0.64
     couverts
    -0.64
     voient
    -0.63
     trasmissione
    -0.61
     due
    -0.60
     tremp
    -0.60
     traduit
    -0.60
    POSITIVE LOGITS
    TypedDataSet
    0.60
     real
    0.54
    IntoConstraints
    0.53
     neu
    0.51
     mischief
    0.50
    KURZBESCHREIBUNG
    0.49
     TPS
    0.49
     pup
    0.49
     Credo
    0.48
     virgin
    0.48
    Activations Density 11.433%

    No Known Activations