© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10438
    Prev
    Next
    INDEX
    Explanations

    the words "grand," "them," cream," and "system," sometimes in proximity to each other.

    oai_token-act-pair · gemini-2.0-flash

    grand

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     orec
    -0.67
    The
    -0.59
     orel
    -0.57
    USE
    -0.53
    <strong>
    -0.53
    Original
    -0.52
    '
    -0.52
    the
    -0.51
     
    -0.51
    по
    -0.50
    POSITIVE LOGITS
     дописавши
    1.20
    tagext
    1.14
    principalColumn
    1.11
    
    1.10
    XMLSchema
    1.09
     doubtnut
    1.09
    ]")]
    1.05
     ModelExpression
    1.05
     MessageBoxIcon
    1.04
    Personensuche
    1.03
    Activations Density 1.985%

    No Known Activations