© 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. 13724
    Prev
    Next
    INDEX
    Explanations

    words relating to scientific processes and characterization.

    oai_token-act-pair · gemini-2.0-flash

    scientific processes

    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
    saraba
    -0.91
    oredCriteria
    -0.90
     للاسماء
    -0.85
     CreateTagHelper
    -0.83
    complexContent
    -0.83
    Autoritní
    -0.82
     autorytatywna
    -0.78
    OGND
    -0.77
    tvguidetime
    -0.75
    #+#
    -0.73
    POSITIVE LOGITS
    StructEnd
    0.46
    segue
    0.44
    CloseOperation
    0.42
     Ausgleich
    0.41
    セン
    0.38
    fVar
    0.38
    mapper
    0.36
    yorsunuz
    0.35
     audio
    0.35
    arResult
    0.34
    Activations Density 5.247%

    No Known Activations