© 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. 14985
    Prev
    Next
    INDEX
    Explanations

    software license disclaimers

    oai_token-act-pair · gemini-2.0-flash

    Code license agreement

    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
     see
    -1.25
     find
    -1.19
     make
    -1.18
     keep
    -1.14
     don
    -1.13
     give
    -1.13
     know
    -1.10
     look
    -1.09
     take
    -1.07
     remember
    -1.07
    POSITIVE LOGITS
     midterm
    0.55
     atro
    0.54
     interim
    0.54
     eventual
    0.52
     epidemic
    0.52
     opposition
    0.51
     early
    0.51
     academic
    0.51
     anti
    0.50
     activist
    0.50
    Activations Density 11.808%

    No Known Activations