© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10275
    Prev
    Next
    INDEX
    Explanations

    code-related words like "supported", "available", "def", and "practice", and words meaning not useful such as "recommended" and "required."

    oai_token-act-pair · gemini-2.0-flash

    supported/recommended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    LookAnd
    -0.85
     HasFactory
    -0.75
    AutoScaleMode
    -0.75
     invokingState
    -0.72
     '{@
    -0.69
    IUrlHelper
    -0.67
    writeFieldEnd
    -0.63
    MENAFN
    -0.62
    FailureListener
    -0.60
    ViewFeatures
    -0.60
    POSITIVE LOGITS
    <bos>
    0.80
     uncommon
    0.56
     recommended
    0.54
     advisable
    0.51
     available
    0.51
     تانيه
    0.50
     plantilla
    0.49
    PreferredItem
    0.48
     становника
    0.48
     rare
    0.47
    Activations Density 1.341%

    No Known Activations