© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15804
    Prev
    Next
    INDEX
    Explanations

    references to news programs.

    oai_token-act-pair · gemini-2.0-flash

    news show

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    complexType
    -0.63
    __(/*!
    -0.54
     tuyển
    -0.49
     onCreateView
    -0.49
     size
    -0.47
     fly
    -0.46
    исленность
    -0.46
    ESSIONS
    -0.44
     gold
    -0.44
     Fly
    -0.44
    POSITIVE LOGITS
     myſelf
    0.62
     Efq
    0.60
     diſt
    0.59
     disambiguazione
    0.59
     MonoBehaviour
    0.57
     Diſ
    0.56
     whoſe
    0.56
     Reſ
    0.54
     itſelf
    0.53
     Paradox
    0.52
    Activations Density 0.752%

    No Known Activations