© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 12442
    Prev
    Next
    INDEX
    Explanations

    the word "dose" or numbers that could be embedded within a number

    oai_token-act-pair · gemini-2.0-flash

    dose

    np_max-act · gemini-2.0-flash

    ▁dose

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    2
    -1.38
    1
    -1.34
    0
    -1.25
    3
    -1.23
    4
    -1.12
    8
    -1.09
    6
    -1.09
    7
    -1.09
    9
    -1.07
    5
    -1.04
    POSITIVE LOGITS
    )");
    1.69
    ".
    1.67
    "):
    1.60
    .)}
    1.51
     }}$}
    1.48
    '):
    1.46
     ")
    1.43
    )*/
    1.40
    ^(@)
    1.39
    ."));
    1.38
    Activations Density 2.044%

    No Known Activations