© 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. 11298
    Prev
    Next
    INDEX
    Explanations

    instances of the string "und" followed by a space or one or more letters

    oai_token-act-pair · gemini-2.0-flash

    und

    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
    Portale
    -0.61
    ELTS
    -0.58
    ITTLE
    -0.53
    __).
    -0.52
    CLUYE
    -0.52
     alam
    -0.50
    >[]
    -0.49
    AGED
    -0.49
     Samb
    -0.49
    getSystemService
    -0.49
    POSITIVE LOGITS
    Aholisi
    0.63
     cherchés
    0.59
     Meksiku
    0.59
    oa̍t
    0.56
    Hochspringen
    0.52
    NamedQueries
    0.52
    ReusableCell
    0.51
    DrawerToggle
    0.51
    issantes
    0.49
    XmlAccessorType
    0.48
    Activations Density 0.914%

    No Known Activations