© 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. 258
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain dots in conjunction with other code-related keywords

    oai_token-act-pair · gemini-2.0-flash

    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
     AssemblyCulture
    -0.77
    AddTagHelper
    -0.77
    بوابة
    -0.77
     سكانية
    -0.76
     bezeichneter
    -0.73
     saites
    -0.72
    verwijspagina
    -0.69
    vician
    -0.69
    })`
    -0.68
     فريبيس
    -0.63
    POSITIVE LOGITS
     objectAtIndex
    0.51
    GetEnumerator
    0.49
    toJSONString
    0.49
    strictEqual
    0.47
    putchar
    0.46
    opat
    0.45
    toupper
    0.44
    isalpha
    0.44
    OrWhiteSpace
    0.43
    mpotent
    0.42
    Activations Density 4.684%

    No Known Activations