© 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. 4752
    Prev
    Next
    INDEX
    Explanations

    variable assignments, particularly the word 'held' and agricultural terms

    oai_token-act-pair · gemini-2.0-flash

    stability

    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
    VersionUID
    -0.53
     AssemblyTitle
    -0.52
    ньше
    -0.47
    urtz
    -0.46
     friv
    -0.46
    GenerationType
    -0.46
    zewski
    -0.44
    نگار
    -0.44
    indiri
    -0.43
    ImageContext
    -0.43
    POSITIVE LOGITS
     stable
    1.59
     fixed
    1.53
     constancy
    1.52
     constant
    1.48
    fixed
    1.37
    Fixed
    1.36
     Fixed
    1.35
     Stable
    1.34
    constant
    1.34
    stable
    1.34
    Activations Density 2.944%

    No Known Activations