© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10258
    Prev
    Next
    INDEX
    Explanations

    bulleted lists, question marks, and all-caps words

    oai_token-act-pair · gemini-2.0-flash

    question marks and bullet points

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    IntoConstraints
    -0.50
     AssemblyTitle
    -0.50
    <bos>
    -0.49
    met
    -0.43
     ModelExpression
    -0.42
    ref
    -0.41
    yt
    -0.41
     concentrates
    -0.40
    FieldDescriptor
    -0.40
    +:+
    -0.40
    POSITIVE LOGITS
     leaſt
    0.57
     Theſe
    0.57
     Efq
    0.56
     purpoſe
    0.52
    Искәрмәләр
    0.51
     becauſe
    0.51
     reaſon
    0.50
    حوالہ
    0.48
    TagHelper
    0.45
     greateſt
    0.44
    Activations Density 0.190%

    No Known Activations