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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12284
    Prev
    Next
    INDEX
    Explanations

    code snippets from software

    oai_token-act-pair · gemini-2.0-flash

    operating systems and technology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     o
    -1.70
     O
    -1.68
    O
    -1.58
     os
    -1.58
     Os
    -1.57
    Os
    -1.55
     OS
    -1.55
    OS
    -1.52
    OC
    -1.38
     OC
    -1.38
    POSITIVE LOGITS
     ModelRenderer
    0.50
    rrggbb
    0.46
    łon
    0.45
    ieder
    0.40
    belajaran
    0.38
    ưởng
    0.38
    eriksaan
    0.36
    iedler
    0.36
    matitis
    0.36
     CONTRIBUTOR
    0.36
    Activations Density 1.946%

    No Known Activations