© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9700
    Prev
    Next
    INDEX
    Explanations

    instances of the author talking about themselves and offering an opinion

    oai_token-act-pair · gemini-2.0-flash

    expressing an opinion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ]--;
    -0.72
     ویکی‌پدی
    -0.68
    ikala
    -0.68
     houſe
    -0.66
    intenance
    -0.63
    Démographie
    -0.63
    rosia
    -0.63
    Composable
    -0.62
    tersebut
    -0.61
    tison
    -0.61
    POSITIVE LOGITS
    inheritdoc
    0.45
    ürm
    0.45
    GEBURTSDATUM
    0.43
    aarrggbb
    0.43
    Gu
    0.42
     aanbod
    0.42
    setopt
    0.41
     $
    0.41
    bec
    0.40
    InjectAttribute
    0.39
    Activations Density 0.611%

    No Known Activations