© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2647
    Prev
    Next
    INDEX
    Explanations

    the word "and" preceded and/or followed by a dash

    oai_token-act-pair · gemini-2.0-flash

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ografija
    -0.66
    SequentialGroup
    -0.66
    GenerationType
    -0.65
    Bronnen
    -0.64
    sibilité
    -0.61
     doInBackground
    -0.59
    intios
    -0.59
     nakalista
    -0.59
    AnchorStyles
    -0.59
     समीक्षक
    -0.59
    POSITIVE LOGITS
    paramref
    0.52
    الإنجليزية
    0.51
    essler
    0.49
    VARI
    0.48
     -
    0.47
    guson
    0.46
    XmlAccessorType
    0.46
     weeks
    0.46
     
    0.46
     And
    0.45
    Activations Density 1.808%

    No Known Activations