© 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. 4655
    Prev
    Next
    INDEX
    Explanations

    language related to slot machines, especially vocabulary related to payout structure

    oai_token-act-pair · gemini-2.0-flash

    wins

    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
     صوتيه
    -1.12
     تضيفلها
    -0.84
    RenderAtEndOf
    -0.83
    RectangleBorder
    -0.78
    Diweddarwch
    -0.77
    UnusedPrivate
    -0.75
     незавершена
    -0.75
    URLException
    -0.73
    WebElementEntity
    -0.72
     كومونز
    -0.71
    POSITIVE LOGITS
    igram
    0.47
     ché
    0.43
    Composable
    0.42
     scel
    0.41
    ỏa
    0.40
    卯
    0.40
    ⌘
    0.40
    くれます
    0.39
     Lom
    0.38
    Selected
    0.38
    Activations Density 6.414%

    No Known Activations