© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4414
    Prev
    Next
    INDEX
    Explanations

    text discussing mental health challenges and/or online shopping deals

    oai_token-act-pair · 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
    وصلات
    -0.70
    Sklici
    -0.69
    PreExecute
    -0.67
    Geplaatst
    -0.67
     utafitiHapana
    -0.66
     كومونز
    -0.66
    migrationBuilder
    -0.65
    viewDidLoad
    -0.65
    imageshack
    -0.65
    показания
    -0.64
    POSITIVE LOGITS
    colgroup
    0.48
     anal
    0.41
    nor
    0.41
    饋
    0.39
     enviable
    0.39
    Nor
    0.39
    nologi
    0.38
     axis
    0.38
     judic
    0.38
    山西
    0.37
    Activations Density 3.228%

    No Known Activations