© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10876
    Prev
    Next
    INDEX
    Explanations

    HTTP error codes

    oai_token-act-pair · gemini-2.0-flash

    HTTP error codes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    tvguidetime
    -0.88
    APORE
    -0.71
    anskje
    -0.67
    \{\\
    -0.66
     OnInit
    -0.66
    μβρίου
    -0.66
    MLLoader
    -0.65
    
    -0.62
     endblock
    -0.61
    "]/
    -0.61
    POSITIVE LOGITS
    0
    0.61
    2
    0.52
    1
    0.47
     wikipagina
    0.46
     commerciales
    0.44
     Dumnezeu
    0.42
    elemField
    0.40
     fotografico
    0.40
    seamnă
    0.40
     lettura
    0.38
    Activations Density 0.797%

    No Known Activations