© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6258
    Prev
    Next
    INDEX
    Explanations

    a setting such as a castle, hall, living room and activities that occur within it.

    oai_token-act-pair · gemini-2.0-flash

    Morning or royalty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     يتيمه
    -1.09
     rhestr
    -0.82
    SequentialGroup
    -0.82
    fjspx
    -0.79
    Портали
    -0.79
    SEGUIR
    -0.79
     myſelf
    -0.77
    matchCondition
    -0.76
     ―――――
    -0.75
    complexType
    -0.74
    POSITIVE LOGITS
    <bos>
    1.19
    '
    0.64
    .
    0.59
    ’
    0.57
    ↵
    0.55
    A
    0.55
    I
    0.54
    of
    0.52
    O
    0.51
    by
    0.51
    Activations Density 1.130%

    No Known Activations