© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7214
    Prev
    Next
    INDEX
    Explanations

    job titles and organization types

    oai_token-act-pair · gemini-2.0-flash

    executive

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    __':
    -0.85
    RegressionTest
    -0.82
    DeleteBehavior
    -0.77
     Hongrie
    -0.76
    __':
    -0.72
     avoient
    -0.70
    IsMutable
    -0.69
     Roskov
    -0.68
     ErrIntOverflow
    -0.68
    lgari
    -0.68
    POSITIVE LOGITS
    idiv
    0.42
     déb
    0.39
    cydow
    0.38
     regia
    0.38
     rec
    0.38
     poj
    0.38
    Personensuche
    0.37
    rizona
    0.37
     recital
    0.37
     administ
    0.36
    Activations Density 4.039%

    No Known Activations