© 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. 10138
    Prev
    Next
    INDEX
    Explanations

    words relating to answering a question or configuring something

    oai_token-act-pair · gemini-2.0-flash

    of/to

    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
    '
    -0.45
    owned
    -0.43
    tanleria
    -0.43
    ’
    -0.42
    原始内容存档于
    -0.41
     posso
    -0.40
    yo
    -0.40
    BeginContext
    -0.40
     accommodated
    -0.40
     cromo
    -0.39
    POSITIVE LOGITS
     InputDecoration
    0.88
    StructEnd
    0.83
    principalColumn
    0.83
     esternos
    0.76
     resourceCulture
    0.69
    󠁴
    0.68
    }]
    0.68
    varlak
    0.68
    addCriterion
    0.67
    +:+
    0.67
    Activations Density 4.228%

    No Known Activations