© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12676
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically HTML and PHP tags as well as JSON

    oai_token-act-pair · gemini-2.0-flash

    programming code

    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
    ArgsConstructor
    -0.72
    InjectAttribute
    -0.64
    .<
    -0.56
     Réponses
    -0.55
    первых
    -0.55
    Kjelder
    -0.53
    ,<
    -0.53
     Luxemburg
    -0.53
    “…
    -0.53
     McFarland
    -0.52
    POSITIVE LOGITS
     endblock
    0.54
    ++
    0.53
     intptr
    0.52
    ,:);
    0.47
     }}"></
    0.47
    vari
    0.47
     gyhoeddwyd
    0.47
    :]:
    0.46
     }}"
    0.45
    enderror
    0.45
    Activations Density 5.367%

    No Known Activations