© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 519
    Prev
    Next
    INDEX
    Explanations

    code or possibly parts of code

    oai_token-act-pair · gemini-2.0-flash

    Code and error messages

    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
     otomatig
    -1.13
    styleType
    -1.01
    "])
    -0.92
    "]);
    -0.90
    "]).
    -0.87
     Administrativna
    -0.85
    ]),
    -0.85
     дописавши
    -0.84
    )");
    -0.84
    adpleegd
    -0.83
    POSITIVE LOGITS
    0.39
    
    0.37
    printf
    0.36
    0.35
    0.34
    0.34
    cos
    0.32
    é
    0.30
    //
    0.30
    عد
    0.29
    Activations Density 2.923%

    No Known Activations