© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2615
    Prev
    Next
    INDEX
    Explanations

    code snippets, code-related terms, and API references

    oai_token-act-pair · gemini-2.0-flash

    Code and API calls

    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
     propOrder
    -0.70
    OrBuilder
    -0.64
     Roskov
    -0.63
    kloped
    -0.57
     actionMode
    -0.53
    ragalactic
    -0.52
     createState
    -0.52
    ftagPool
    -0.51
    ỡng
    -0.51
     EconPapers
    -0.51
    POSITIVE LOGITS
    PreAuthorize
    0.53
    begriff
    0.51
     renang
    0.46
    RequestOptions
    0.46
    ModelForm
    0.44
    conio
    0.44
    SignIn
    0.43
     hutan
    0.43
    Véase
    0.43
     getUsers
    0.43
    Activations Density 8.768%

    No Known Activations