© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8128
    Prev
    Next
    INDEX
    Explanations

    java code snippets with keywords like "new", "public", and "override"

    oai_token-act-pair · gemini-2.0-flash

    public

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     houſe
    -0.84
     neceff
    -0.82
     ſtate
    -0.79
     tranſ
    -0.79
     greateſt
    -0.79
    RenderAtEndOf
    -0.79
    WriteTagHelper
    -0.78
     poffe
    -0.78
     pleaſure
    -0.78
     raiſ
    -0.77
    POSITIVE LOGITS
     ausencia
    0.46
     dommages
    0.45
    vård
    0.43
     inalámb
    0.42
     to
    0.42
     cálculos
    0.41
     reconnaître
    0.41
     </
    0.40
     diversité
    0.40
     lèvres
    0.40
    Activations Density 2.597%

    No Known Activations