© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6594
    Prev
    Next
    INDEX
    Explanations

    proper names, especially those related to people or organizations.

    oai_token-act-pair · gemini-2.0-flash

    names in legal/academic context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     qashqai
    -0.51
    formazioni
    -0.47
    noinspection
    -0.46
     morire
    -0.46
    حوالہ
    -0.46
    atterson
    -0.44
    lepaskan
    -0.44
    Bounding
    -0.44
     milho
    -0.43
    EMPO
    -0.43
    POSITIVE LOGITS
    rubin
    0.68
     Pearls
    0.66
    /**
    0.63
     Gold
    0.63
    ItemBackground
    0.61
    Gold
    0.59
     Marcus
    0.58
     Levin
    0.58
     Lesser
    0.57
    Marcus
    0.56
    Activations Density 3.565%

    No Known Activations