© 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. 11084
    Prev
    Next
    INDEX
    Explanations

    the partial string "qu"

    oai_token-act-pair · gemini-2.0-flash

    qu

    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
    MigrationBuilder
    -0.71
     CURIAM
    -0.57
     asemenea
    -0.47
    andReturn
    -0.45
    XMLSchema
    -0.44
     schme
    -0.41
    PRNewswire
    -0.41
     respectivamente
    -0.41
    isNotEmpty
    -0.40
     monopo
    -0.39
    POSITIVE LOGITS
    rrggbb
    0.59
     appelez
    0.56
    isier
    0.55
    NameInMap
    0.54
     bezeichneter
    0.54
    ghed
    0.53
     Rivas
    0.52
    enumii
    0.51
     Devlin
    0.50
    expandindo
    0.49
    Activations Density 0.767%

    No Known Activations