© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2569
    Prev
    Next
    INDEX
    Explanations

    code snippets and logs related to data processing, numerical calculations, and web development

    oai_token-act-pair · gemini-2.0-flash

    extrema and bounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Fredrik
    -0.54
     Fä
    -0.52
    ophora
    -0.50
     अंतर
    -0.50
     αι
    -0.50
    klaim
    -0.50
     interpolated
    -0.47
     impracticable
    -0.46
     transcends
    -0.46
    resa
    -0.46
    POSITIVE LOGITS
    ++
    0.66
    igshid
    0.66
     kaynağından
    0.59
    CGRectMake
    0.58
    ScreenState
    0.56
    katapos
    0.55
    estacks
    0.54
    "?>
    0.52
    UnusedPrivate
    0.52
    DOCTYPE
    0.51
    Activations Density 68.532%

    No Known Activations