© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14345
    Prev
    Next
    INDEX
    Explanations

    descriptions of how to creatively save space

    oai_token-act-pair · gemini-2.0-flash

    including

    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
    WireFormatLite
    -0.86
    MessageOf
    -0.77
    matchCondition
    -0.69
    writeField
    -0.68
    IsMutable
    -0.67
     ProtoMessage
    -0.66
    WaitGroup
    -0.63
    LabelTagHelper
    -0.60
    ValueStyle
    -0.59
    AddTagHelper
    -0.56
    POSITIVE LOGITS
    </thead>
    0.53
     Schülern
    0.51
    erequisites
    0.49
     addUser
    0.47
    RenderAtEndOf
    0.45
    ISTRATION
    0.44
    dimer
    0.42
    ValueType
    0.42
    UpdateUser
    0.42
    leigh
    0.41
    Activations Density 3.332%

    No Known Activations