© 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. 11208
    Prev
    Next
    INDEX
    Explanations

    the letter "o" followed by a digit or specific words like "mer" or "ze".

    oai_token-act-pair · gemini-2.0-flash

    o

    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
    PerformLayout
    -1.02
     kasarigan
    -0.99
     OFDb
    -0.93
     فريبيس
    -0.80
    verwijspagina
    -0.79
     للمعارف
    -0.79
    Geplaatst
    -0.77
    PreferredItem
    -0.77
     utafitiHapana
    -0.77
    DispatchToProps
    -0.76
    POSITIVE LOGITS
    up
    0.59
    cha
    0.46
    chi
    0.43
    vi
    0.41
    lar
    0.41
    chan
    0.39
    var
    0.38
    du
    0.38
    dic
    0.38
    zen
    0.38
    Activations Density 4.140%

    No Known Activations