© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14259
    Prev
    Next
    INDEX
    Explanations

    dates, especially those including the month.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     selfies
    -0.60
     selfie
    -0.56
    nologies
    -0.56
     microbiome
    -0.52
    IGO
    -0.52
     dédié
    -0.50
    횟
    -0.50
     dédi
    -0.50
     travers
    -0.50
    OrWhiteSpace
    -0.49
    POSITIVE LOGITS
    AsUp
    0.82
     mußten
    0.72
    ^(@)
    0.70
     läßt
    0.69
     doubtnut
    0.68
    ]))
    0.67
     Daß
    0.64
     ]
    0.63
     Rptr
    0.62
    };*/
    0.62
    Activations Density 35.198%

    No Known Activations