© 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. 17
    Prev
    Next
    INDEX
    Explanations

    a variety of numbers, locations, and ordinal adjectives

    oai_token-act-pair · gemini-2.0-flash

    Business clients

    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
     vidare
    -0.38
    shadowOffset
    -0.37
     betyd
    -0.36
     matiz
    -0.36
    aternion
    -0.34
    __.__
    -0.34
    ÍSTICAS
    -0.34
     rör
    -0.34
    uronic
    -0.33
    éron
    -0.33
    POSITIVE LOGITS
     clients
    0.91
     consultation
    0.91
     client
    0.88
     consultations
    0.87
     recruitment
    0.87
     Clients
    0.84
     Consultation
    0.84
     recruiting
    0.82
    Clients
    0.82
     attendee
    0.80
    Activations Density 20.631%

    No Known Activations