© 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. 14783
    Prev
    Next
    INDEX
    Explanations

    mentions of coupons, offers, and licenses

    oai_token-act-pair · gemini-2.0-flash

    Licenses and coupons

    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
     cheapest
    -0.89
    best
    -0.80
     best
    -0.80
     buy
    -0.78
     bonus
    -0.77
     AssemblyTitle
    -0.77
     premium
    -0.77
     price
    -0.76
    bonus
    -0.76
     cheaper
    -0.75
    POSITIVE LOGITS
     mountains
    0.59
     view
    0.59
     discussion
    0.58
     conversation
    0.58
     dialog
    0.57
     scene
    0.56
     journey
    0.55
     questioning
    0.55
     road
    0.54
     discourse
    0.54
    Activations Density 9.002%

    No Known Activations