© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    various contexts involving sports, business interactions, and time-sensitive occurrences

    oai_token-act-pair · gemini-2.0-flash

    list of names

    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
     Bob
    -1.46
     Jim
    -1.45
     Tom
    -1.41
     Bill
    -1.34
    Bob
    -1.30
    Jim
    -1.30
     Dave
    -1.24
     JIM
    -1.23
     bob
    -1.23
    Bill
    -1.21
    POSITIVE LOGITS
     متعلقه
    0.63
    Бахар
    0.47
     moletom
    0.46
    Beijo
    0.46
     nė
    0.44
    MBR
    0.42
     sereia
    0.41
    zyż
    0.41
     pleaſure
    0.40
    complexContent
    0.39
    Activations Density 1.753%

    No Known Activations