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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5966
    Prev
    Next
    INDEX
    Explanations

    descriptions of geographical locations with rough terrain like caves, rocks, and valleys

    oai_token-act-pair · gemini-2.0-flash

    landscapes

    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
    ítmény
    -0.49
    شوف
    -0.49
    клопе
    -0.48
    thâu
    -0.48
    ayaquil
    -0.46
    AndroidJUnit
    -0.46
    олові
    -0.45
    Worth
    -0.45
     للاسماء
    -0.45
    نجليزية
    -0.45
    POSITIVE LOGITS
    verwijspagina
    0.71
     AssemblyCulture
    0.63
    bootstrapcdn
    0.61
     resourceCulture
    0.58
     ApiException
    0.58
    NegativeButton
    0.57
    Rhestr
    0.57
    PositiveButton
    0.57
    jsonwebtoken
    0.57
     AssemblyVersion
    0.57
    Activations Density 8.043%

    No Known Activations