© 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. 4477
    Prev
    Next
    INDEX
    Explanations

    words related to health and size/weight

    oai_token-act-pair · gemini-2.0-flash

    end in yp/ily/ym

    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
    ScopeManager
    -0.68
    AndroidJUnit
    -0.66
    TagHelpers
    -0.63
    SourceChecksum
    -0.63
    MarshalTo
    -0.63
     Vikipedi
    -0.63
    DotNetBar
    -0.62
    yntaxException
    -0.60
     &___
    -0.59
     صوتيه
    -0.59
    POSITIVE LOGITS
    yp
    0.69
    ily
    0.65
    ym
    0.63
    yd
    0.63
    ys
    0.61
    ying
    0.58
    yer
    0.55
    TextFormField
    0.52
    yb
    0.52
    yle
    0.52
    Activations Density 1.855%

    No Known Activations