© 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. 5810
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to program debugging and execution within a computer system

    oai_token-act-pair · gemini-2.0-flash

    Code and technical documents

    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
     BR
    -1.71
     Bra
    -1.70
    Bra
    -1.68
     Br
    -1.68
     Bro
    -1.66
     BRA
    -1.66
    Bro
    -1.65
     BRO
    -1.61
     Bre
    -1.59
    Br
    -1.59
    POSITIVE LOGITS
     الحره
    0.60
    ög
    0.44
    scm
    0.44
     goutte
    0.42
     ilm
    0.40
     Qiu
    0.40
     ccm
    0.40
     Magdalena
    0.40
     fauteuil
    0.39
    西瓜
    0.39
    Activations Density 1.041%

    No Known Activations