© 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. 11951
    Prev
    Next
    INDEX
    Explanations

    named entities and their relationships in the context of the Harry Potter series

    oai_token-act-pair · 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
    يكا
    -0.45
     senses
    -0.43
     CTP
    -0.43
    Tikang
    -0.43
     Arad
    -0.42
     Pediatrics
    -0.41
     bando
    -0.41
    dafx
    -0.41
    AxisAlignment
    -0.41
     squirrels
    -0.41
    POSITIVE LOGITS
     BoxDecoration
    0.76
     kasarigan
    0.74
    íncia
    0.63
    httphttps
    0.60
     виправивши
    0.60
    VersionUID
    0.60
    rungsseite
    0.58
    verwijspagina
    0.58
    Šaltiniai
    0.57
    Pozri
    0.57
    Activations Density 1.064%

    No Known Activations