© 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. 579
    Prev
    Next
    INDEX
    Explanations

    contextual words such as articles, prepositions and possessive pronouns

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     itſelf
    -0.70
    ſelf
    -0.69
     myſelf
    -0.66
     Houſe
    -0.65
     Anſ
    -0.64
     Reſ
    -0.63
    WriteAttribute
    -0.63
     Theſe
    -0.61
    uxxxx
    -0.61
    Rohy
    -0.59
    POSITIVE LOGITS
    ropriate
    0.52
     ComVisible
    0.44
     blancs
    0.44
    rootScope
    0.43
    
    0.43
     مشين
    0.42
    tableFuture
    0.42
    ContextHolder
    0.40
    området
    0.40
    InitStruct
    0.40
    Activations Density 0.868%

    No Known Activations