© 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. 14463
    Prev
    Next
    INDEX
    Explanations

    HTML tags, URLs, dates or times

    oai_token-act-pair · gemini-2.0-flash

    Blog posts and comments

    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
    finement
    -0.43
    enchymal
    -0.40
    OCC
    -0.39
    xtension
    -0.37
     rou
    -0.37
    TabLayout
    -0.37
     Knie
    -0.36
    utnik
    -0.36
    otonic
    -0.35
    orrhage
    -0.35
    POSITIVE LOGITS
    contentLoaded
    0.80
     AssemblyVersion
    0.68
    __':
    0.68
    MessageTagHelper
    0.67
    horabuena
    0.65
    __":
    0.65
    ParallelGroup
    0.65
     favorites
    0.64
    }))
    0.64
     køb
    0.63
    Activations Density 14.140%

    No Known Activations