© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12887
    Prev
    Next
    INDEX
    Explanations

    words related to scientific publications and reporting results

    oai_token-act-pair · gemini-2.0-flash

    persistence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    таратура
    -0.48
     demek
    -0.47
    Données
    -0.46
    hdys
    -0.46
     idem
    -0.46
     domo
    -0.46
     explodes
    -0.45
     Efq
    -0.45
    uego
    -0.45
    postsleuth
    -0.44
    POSITIVE LOGITS
    MigrationBuilder
    0.72
     nahilalakip
    0.71
     intptr
    0.69
    }\]
    0.69
    }();
    0.67
    Datuak
    0.66
    }()
    0.63
    tagHelperRunner
    0.63
     محفوظة
    0.63
    Rüyada
    0.60
    Activations Density 10.869%

    No Known Activations