© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12654
    Prev
    Next
    INDEX
    Explanations

    scientific language related to complex systems, possibly ecological or geographical

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    ワー
    -0.49
    심
    -0.46
    er
    -0.45
    -
    -0.44
     W
    -0.43
     including
    -0.43
    l
    -0.41
    hain
    -0.41
    lab
    -0.41
    —
    -0.40
    POSITIVE LOGITS
    CloseOperation
    0.84
    TintMode
    0.77
     onAnimation
    0.76
     CreateTagHelper
    0.75
    LookAnd
    0.74
    featureID
    0.69
     سكانية
    0.68
     AttributeSet
    0.68
    følgelig
    0.68
    ArgsConstructor
    0.66
    Activations Density 5.566%

    No Known Activations