© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4095
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain syntax, variable names, and comments

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     autorytatywna
    -0.90
     femininas
    -0.89
     igång
    -0.87
     avoient
    -0.86
     säll
    -0.84
     brancas
    -0.83
     varandra
    -0.82
     صوتيه
    -0.81
     mourut
    -0.79
     Anſ
    -0.78
    POSITIVE LOGITS
     the
    1.08
     a
    0.85
     an
    0.76
     our
    0.75
     
    0.71
     di
    0.71
     his
    0.64
     all
    0.63
     her
    0.63
     this
    0.63
    Activations Density 8.598%

    No Known Activations