© 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. 8337
    Prev
    Next
    INDEX
    Explanations

    common words like "the", "at", "be", "will", or words that imply wanting, knowledge, or turning out a certain way.

    oai_token-act-pair · gemini-2.0-flash

    technical contexts

    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
     Better
    -2.14
    Better
    -2.13
    better
    -2.08
     better
    -2.02
     BETTER
    -1.82
     melhor
    -1.55
     worse
    -1.53
     mejor
    -1.51
    Mejor
    -1.45
    worse
    -1.44
    POSITIVE LOGITS
     Catawiki
    0.73
    ImageContext
    0.58
     ctypes
    0.54
    Personensuche
    0.52
    Дереккөздер
    0.52
    ">//
    0.51
    PropertyChanging
    0.51
    Források
    0.48
    PhysRevLett
    0.48
     columnIndex
    0.48
    Activations Density 2.409%

    No Known Activations