© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5254
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    x

    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
    e
    -0.60
     
    -0.59
    x
    -0.59
    a
    -0.57
    ne
    -0.53
    b
    -0.52
    ca
    -0.50
    ma
    -0.50
    di
    -0.49
    ix
    -0.48
    POSITIVE LOGITS
     Roskov
    1.16
    rungsseite
    0.98
     kasarigan
    0.92
    featureID
    0.92
     ExecuteAsync
    0.92
     gynhyrchwyd
    0.90
     ProtoMessage
    0.89
    InjectAttribute
    0.88
     disambiguazione
    0.87
    MigrationBuilder
    0.85
    Activations Density 0.783%

    No Known Activations