© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3429
    Prev
    Next
    INDEX
    Explanations

    code snippets and JSON-like data structures and the words "radio","true", "string", and "uri"

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    ########.
    -0.97
     disambiguazione
    -0.97
    GEBURTSDATUM
    -0.94
    RenderAtEndOf
    -0.89
    .")
    -0.80
    ंदीखरीदारी
    -0.79
     allAfrica
    -0.78
    IndentedString
    -0.77
     Roskov
    -0.76
    ValueStyle
    -0.75
    POSITIVE LOGITS
     diikuti
    0.49
     paj
    0.44
     suivie
    0.44
     suivi
    0.43
    setUserId
    0.43
    TRAILING
    0.41
    }
    0.41
    katapos
    0.40
     Mess
    0.40
     seguida
    0.40
    Activations Density 10.787%

    No Known Activations