© 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. 15971
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially file paths and code elements such as variables, function names, and language keywords.

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
     NSCoder
    -0.63
    Parcelize
    -0.61
    bewerken
    -0.61
     виправивши
    -0.59
     HasFactory
    -0.58
    Демографія
    -0.58
    OGND
    -0.57
     ControllerBase
    -0.57
    +#+#
    -0.56
     ContentValues
    -0.54
    POSITIVE LOGITS
    n
    0.55
    tagHelperRunner
    0.51
    nt
    0.51
    rt
    0.49
    br
    0.48
    g
    0.48
    nj
    0.47
    nter
    0.47
    lj
    0.47
    ntr
    0.46
    Activations Density 17.660%

    No Known Activations