© 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. 12503
    Prev
    Next
    INDEX
    Explanations

    occurrences of the first-person pronoun and indicators of questions which could be posed by a user.

    oai_token-act-pair · gemini-2.0-flash

    code and technical text

    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
     knji
    -0.28
    })+\
    -0.24
    bindParam
    -0.22
     раз
    -0.21
    förs
    -0.21
    inin
    -0.19
     WARNING
    -0.19
    ah
    -0.19
    ina
    -0.19
    addTo
    -0.19
    POSITIVE LOGITS
    OGND
    0.95
    RegistryLite
    0.93
    :✨
    0.91
    ChildScrollView
    0.89
    NameInMap
    0.88
    XmlAccessType
    0.88
     Савезне
    0.88
    CloseOperation
    0.87
    IonicModule
    0.86
    contentLoaded
    0.84
    Activations Density 33.534%

    No Known Activations