© 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. 10932
    Prev
    Next
    INDEX
    Explanations

    tokens associated with allowing something

    oai_token-act-pair · gemini-2.0-flash

    leaving/allowing to leave

    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
     CreateTagHelper
    -0.91
    PerformLayout
    -0.80
     Roskov
    -0.69
     تضيفلها
    -0.65
    protoc
    -0.63
     resourceCulture
    -0.61
    CPtr
    -0.60
    gonic
    -0.60
    abstractmethod
    -0.60
    脚注の使い方
    -0.59
    POSITIVE LOGITS
     graag
    0.68
     tolerated
    0.57
    χρι
    0.54
    haba
    0.53
     residue
    0.52
     liever
    0.49
    Scaler
    0.49
     /\.
    0.49
    limus
    0.48
     Sublime
    0.48
    Activations Density 1.149%

    No Known Activations