© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12677
    Prev
    Next
    INDEX
    Explanations

    mentions of something interesting, funny, difficult, or frustrating.

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Мексичка
    -0.96
    (!__
    -0.93
    StoryboardSegue
    -0.91
    ImageContext
    -0.83
    ]--;
    -0.82
     Roskov
    -0.81
    Демографія
    -0.81
     protoimpl
    -0.80
    abestanden
    -0.80
    脚注の使い方
    -0.77
    POSITIVE LOGITS
     part
    3.52
    part
    3.11
    Part
    2.88
     Part
    2.67
     parte
    2.63
     parts
    2.59
     PART
    2.33
    parts
    2.23
     Teil
    2.14
    PART
    2.05
    Activations Density 2.720%

    No Known Activations