© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13491
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to relationships or connections

    oai_token-act-pair · gemini-2.0-flash

    relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    routeProvider
    -0.49
    ioutil
    -0.46
     oscill
    -0.45
     للاسماء
    -0.43
    (")");
    -0.43
     tartalomajánló
    -0.42
    landı
    -0.42
     sphinx
    -0.41
    UNGE
    -0.40
    ccedil
    -0.40
    POSITIVE LOGITS
     among
    2.84
    among
    2.53
     AMONG
    2.31
     Among
    2.30
     amongst
    2.16
    Among
    2.14
     Amongst
    1.80
     среди
    1.71
     parmi
    1.63
     blant
    1.62
    Activations Density 7.055%

    No Known Activations