© 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. 1179
    Prev
    Next
    INDEX
    Explanations

    the keyword "public" which indicates class definitions in programming languages

    oai_token-act-pair · gemini-2.0-flash

    public

    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
    classes
    -0.66
    CLASSES
    -0.56
     classes
    -0.54
    CLASS
    -0.54
    copy
    -0.51
    orari
    -0.51
    OrEmpty
    -0.50
    ofür
    -0.48
    Classes
    -0.47
    ilder
    -0.47
    POSITIVE LOGITS
    TemporalType
    0.74
     GenerationType
    0.65
    DebuggerNonUser
    0.64
    stateProvider
    0.56
     Alamofire
    0.55
     BufferedImage
    0.53
    +#+#
    0.53
    mybatisplus
    0.53
    ://$
    0.53
    TargetException
    0.52
    Activations Density 0.695%

    No Known Activations