© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4392
    Prev
    Next
    INDEX
    Explanations

    clauses describing people's relationships with projects, sponsors or institutions, especially when denying a role

    oai_token-act-pair · gemini-2.0-flash

    involvement/participation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     tartalomajánló
    -0.54
     كومونز
    -0.54
     Defenders
    -0.52
    出版年
    -0.52
     Terraria
    -0.51
    دانشنامهٔ
    -0.51
     portefeuille
    -0.50
    OPSIS
    -0.50
    chaun
    -0.50
    COUVER
    -0.49
    POSITIVE LOGITS
     involvement
    1.81
     participation
    1.74
     Involvement
    1.66
     role
    1.63
     Participation
    1.54
     involved
    1.51
    Participation
    1.48
     participating
    1.41
    volvement
    1.41
     participate
    1.40
    Activations Density 2.708%

    No Known Activations