© 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. 390
    Prev
    Next
    INDEX
    Explanations

    numerical strings and codes

    oai_token-act-pair · gemini-2.0-flash

    Code, numbers, math, dates

    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
    1
    -0.82
    0
    -0.81
    8
    -0.77
    5
    -0.77
    4
    -0.74
    2
    -0.73
    3
    -0.73
    9
    -0.72
    6
    -0.69
    7
    -0.64
    POSITIVE LOGITS
    новниш
    0.84
     AssemblyCulture
    0.82
    +#+#
    0.82
    yakarta
    0.79
    tvguidetime
    0.78
    iffance
    0.78
    útbol
    0.77
    ItemBackground
    0.77
     unknownFields
    0.74
    webElementXpaths
    0.73
    Activations Density 20.457%

    No Known Activations