© 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. 10925
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    oai_token-act-pair · gemini-2.0-flash

    Date/time posts

    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
    StoryboardSegue
    -0.99
     Roskov
    -0.98
     createSlice
    -0.92
    Vidite
    -0.91
     Signalez
    -0.88
    новништво
    -0.86
     שוליים
    -0.84
    WebVitals
    -0.79
     AssemblyVersion
    -0.79
     Reverso
    -0.79
    POSITIVE LOGITS
    :
    0.64
     a
    0.57
     constate
    0.42
     
    0.37
     an
    0.36
    reader
    0.35
     RSSSF
    0.35
    PerformLayout
    0.35
    IDENTITY
    0.34
     reiv
    0.33
    Activations Density 0.665%

    No Known Activations