© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3327
    Prev
    Next
    INDEX
    Explanations

    code snippets or database queries

    oai_token-act-pair · gemini-2.0-flash

    usernames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Roskov
    -0.66
    invokeLater
    -0.52
    LookAnd
    -0.51
    TargetException
    -0.50
    GetMapping
    -0.46
    цездатний
    -0.46
     SCI
    -0.44
    Spoljašnje
    -0.43
    AddTagHelper
    -0.43
    oplastic
    -0.43
    POSITIVE LOGITS
     username
    1.27
     Username
    1.20
    Username
    1.16
     Users
    1.15
     usernames
    1.14
    username
    1.10
     password
    1.08
     User
    1.07
    Users
    1.06
    UserName
    1.05
    Activations Density 16.439%

    No Known Activations