© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9420
    Prev
    Next
    INDEX
    Explanations

    exclamations and end-of-sentence punctuation within different contexts, including fantasy related.

    oai_token-act-pair · gemini-2.0-flash

    Nonsense text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Мексичка
    -0.86
     tears
    -0.75
     screams
    -0.73
     cocked
    -0.70
    SceneManagement
    -0.69
    ValueStyle
    -0.69
    expandindo
    -0.68
    AndEndTag
    -0.67
     blows
    -0.66
     groans
    -0.66
    POSITIVE LOGITS
     hefyd
    0.61
     canaux
    0.48
     églises
    0.46
     högre
    0.46
     peuples
    0.44
     bienes
    0.43
     biens
    0.43
     supérieures
    0.42
    Bryan
    0.42
     estudios
    0.42
    Activations Density 3.279%

    No Known Activations