© 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. 163
    Prev
    Next
    INDEX
    Explanations

    code and programming snippets, potentially across multiple languages

    oai_token-act-pair · gemini-2.0-flash

    data management

    np_max-act-logits · gemini-2.0-flash

    CRUD operations

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    carton
    -0.46
     représentants
    -0.45
     genoux
    -0.44
    antMatchers
    -0.44
     lèvres
    -0.44
     preuves
    -0.44
     blessés
    -0.43
     sœurs
    -0.43
    coupon
    -0.42
     varandra
    -0.42
    POSITIVE LOGITS
     data
    0.69
     current
    0.65
     new
    0.65
     user
    0.63
     method
    0.60
     key
    0.60
     specific
    0.60
     dynamic
    0.60
     initial
    0.59
     access
    0.58
    Activations Density 22.933%

    No Known Activations