© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    html tags or xml-like syntax

    oai_token-act-pair · gemini-2.0-flash

    say "class"

    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
     class
    -2.70
     Class
    -2.47
     classes
    -2.44
     Classes
    -2.33
    class
    -2.31
    Class
    -2.28
     CLASS
    -2.28
    Classes
    -2.14
    classes
    -2.09
     classe
    -2.09
    POSITIVE LOGITS
    DebuggerNonUser
    0.55
    userdetails
    0.43
    stdc
    0.43
    BUR
    0.42
     Wikimedijinoj
    0.42
     Beno
    0.40
     UnityEditor
    0.40
    IntoConstraints
    0.38
    TestUtil
    0.38
    EndContext
    0.38
    Activations Density 1.429%

    No Known Activations