© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10191
    Prev
    Next
    INDEX
    Explanations

    code blocks in a programming language

    oai_token-act-pair · gemini-2.0-flash

    Code/config snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     DBNull
    -0.70
    EDEFAULT
    -0.62
     createState
    -0.60
     Bracken
    -0.60
     يتيمه
    -0.59
    Lähteet
    -0.58
    GenerationType
    -0.57
     صوتيه
    -0.57
    EndInit
    -0.56
    قایناقلار
    -0.55
    POSITIVE LOGITS
    SourceChecksum
    0.63
    0.56
     beginnetje
    0.54
     concor
    0.52
     حد
    0.51
                                  
    0.49
    MathML
    0.49
    ("")]
    0.49
    amor
    0.48
    uxley
    0.47
    Activations Density 0.967%

    No Known Activations