© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5099
    Prev
    Next
    INDEX
    Explanations

    code-related terms having to do with requests, properties, parameters, and options

    oai_token-act-pair · gemini-2.0-flash

    say [the period]

    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
     Roskov
    -0.99
     OFDb
    -0.93
    Jereo
    -0.90
     MainAxisSize
    -0.88
    DeleteBehavior
    -0.85
    RunAsync
    -0.84
    BeginContext
    -0.84
    RepeatedField
    -0.78
     CallOverrides
    -0.78
     BytesLike
    -0.77
    POSITIVE LOGITS
    .
    0.77
    ."
    0.53
    ().
    0.50
    .'
    0.49
    ?.
    0.48
    }$.
    0.47
     ready
    0.46
    ".
    0.45
     mo
    0.44
    .”
    0.44
    Activations Density 2.556%

    No Known Activations