© 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. 8305
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to options and actions

    oai_token-act-pair · gemini-2.0-flash

    action-related terms

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

    Taking action

    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
    ThroughAttribute
    -0.96
    +#+#
    -0.73
    󠁢
    -0.69
     createState
    -0.69
    esModule
    -0.63
     שוליים
    -0.62
     Expertise
    -0.60
    IsContent
    -0.59
    basis
    -0.59
    getWriter
    -0.58
    POSITIVE LOGITS
     ac
    0.76
     act
    0.66
     ACT
    0.63
    Ac
    0.57
     AC
    0.55
     Act
    0.51
     actúa
    0.51
     Ac
    0.51
     acted
    0.50
    액
    0.49
    Activations Density 1.790%

    No Known Activations