© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11253
    Prev
    Next
    INDEX
    Explanations

    the word "append", and to a lesser extent, words related to time

    oai_token-act-pair · gemini-2.0-flash

    append

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <i>
    -0.57
     
    -0.53
     will
    -0.50
    </b>
    -0.50
    CAL
    -0.50
    ong
    -0.49
    <b>
    -0.48
    hip
    -0.48
    The
    -0.47
     signal
    -0.47
    POSITIVE LOGITS
    :✨
    1.60
    تقاوى
    1.36
     ModelExpression
    1.34
    MigrationBuilder
    1.34
     صوتيه
    1.30
     CreateTagHelper
    1.29
     unknownFields
    1.27
    Datuak
    1.27
     Савезне
    1.22
     متعلقه
    1.20
    Activations Density 1.352%

    No Known Activations