© 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. 11907
    Prev
    Next
    INDEX
    Explanations

    dates and numbers formatted with a 1 followed by another number

    oai_token-act-pair · gemini-2.0-flash

    the number one

    np_max-act · gemini-2.0-flash
    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
    <bos>
    -1.41
    2
    -1.05
    4
    -1.03
    3
    -1.03
    1
    -1.02
    ↵
    -0.96
    5
    -0.96
    7
    -0.94
    9
    -0.92
    8
    -0.90
    POSITIVE LOGITS
     kasarigan
    1.10
     WaitForSeconds
    0.94
    astéro
    0.92
    ="@+
    0.90
    ésult
    0.90
    daß
    0.84
    ElementException
    0.83
    GORITH
    0.83
    RuleContext
    0.83
    EMBLY
    0.81
    Activations Density 2.326%

    No Known Activations