© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7975
    Prev
    Next
    INDEX
    Explanations

    geological and construction terms and concepts, especially related to stone and roofing.

    oai_token-act-pair · gemini-2.0-flash

    words related to stone and bricks

    np_token-act-pair-logits · gpt-4o-mini

    brick/bricks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    存于互联网档案馆
    -0.55
     برانيه
    -0.49
    posedge
    -0.48
     AppComponent
    -0.48
    thâu
    -0.45
    Дере
    -0.44
    ianus
    -0.43
     bawang
    -0.43
     Forst
    -0.42
    <?
    -0.42
    POSITIVE LOGITS
     brick
    0.96
     bricks
    0.92
     Brick
    0.82
     <<<<<<<<<<<<<<
    0.79
    brick
    0.79
     lime
    0.78
     Bricks
    0.77
    Brick
    0.72
     stones
    0.72
     stone
    0.72
    Activations Density 1.540%

    No Known Activations