© 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. 15178
    Prev
    Next
    INDEX
    Explanations

    mentions of studies, research, papers, and reports and their related goals

    oai_token-act-pair · gemini-2.0-flash

    this

    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
    -0.68
    })));
    -0.64
     дописавши
    -0.63
    '][$
    -0.62
    webElement
    -0.62
    }}=$
    -0.61
    (")");
    -0.59
     wireType
    -0.58
    脚注の使い方
    -0.58
    RTGC
    -0.57
    POSITIVE LOGITS
     Conventions
    0.45
     seien
    0.45
    ämp
    0.44
     katal
    0.43
    Kesimpulan
    0.43
     vân
    0.43
     Exact
    0.41
    StackNavigator
    0.41
     isComment
    0.41
    semantics
    0.41
    Activations Density 19.758%

    No Known Activations