© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7396
    Prev
    Next
    INDEX
    Explanations

    the word "the" and possessive pronouns, but also reacts positively to mentions of friends and going to the city versus a cottage.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     $_"
    -0.87
     myſelf
    -0.75
     ſeveral
    -0.75
     whoſe
    -0.73
     ſever
    -0.73
     $_(
    -0.73
     juſt
    -0.72
     itſelf
    -0.71
     (\<
    -0.70
     ―――――
    -0.70
    POSITIVE LOGITS
     doInBackground
    0.66
     resourceCulture
    0.66
    ViewFeatures
    0.65
    TagMode
    0.59
    rungsseite
    0.56
    SourceChecksum
    0.53
    ConverterFactory
    0.50
     Roskov
    0.49
    sique
    0.48
     absol
    0.47
    Activations Density 1.726%

    No Known Activations