© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2767
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers

    oai_token-act-pair · gemini-2.0-flash

    third

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     third
    -2.16
    Third
    -1.98
     fourth
    -1.93
    third
    -1.93
     Third
    -1.82
     fifth
    -1.75
    Fourth
    -1.71
     sixth
    -1.70
     seventh
    -1.68
    fourth
    -1.68
    POSITIVE LOGITS
    AxisAlignment
    0.60
    يميديا
    0.56
    getRuntime
    0.54
    Kontrola
    0.51
     Bacteriol
    0.48
     Goya
    0.46
    اعمال
    0.46
     marca
    0.44
     ErrIntOverflow
    0.43
    ubber
    0.43
    Activations Density 5.226%

    No Known Activations