© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8820
    Prev
    Next
    INDEX
    Explanations

    references to characters in a narrative

    oai_token-act-pair · gemini-2.0-flash

    story beginnings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     duide
    -0.53
    >());
    -0.50
    ibol
    -0.50
     chiare
    -0.49
     cancellation
    -0.49
     Bukan
    -0.48
    Erreferentziak
    -0.48
    achal
    -0.48
    Искәрмәләр
    -0.47
     Kości
    -0.47
    POSITIVE LOGITS
    enumii
    0.63
     GenerationType
    0.61
     pinulongan
    0.59
    Geplaatst
    0.59
    richTextPanel
    0.58
     gl
    0.57
    Portale
    0.54
    клопе
    0.54
    BASEPATH
    0.53
     ModelExpression
    0.52
    Activations Density 4.460%

    No Known Activations