© 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. 12356
    Prev
    Next
    INDEX
    Explanations

    long, complex sentences about justice, law and property

    oai_token-act-pair · gemini-2.0-flash

    non-English

    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
    IntoConstraints
    -0.84
    Portail
    -0.82
    FormTagHelper
    -0.81
    Datuak
    -0.79
    SourceChecksum
    -0.76
     getItemCount
    -0.70
    MigrationBuilder
    -0.63
    NOPQRST
    -0.61
     المعيارى
    -0.59
    Tikang
    -0.57
    POSITIVE LOGITS
    csolódó
    0.50
     keş
    0.49
     nahilalakip
    0.48
     Abonnez
    0.47
     inescapable
    0.47
     evolu
    0.47
    ächtig
    0.45
    Severity
    0.45
     dischar
    0.45
     evolucion
    0.45
    Activations Density 8.939%

    No Known Activations