© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10352
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that use "if" and words related to needs

    oai_token-act-pair · gemini-2.0-flash

    Conditional statements

    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
     myſelf
    -1.16
    __":
    
    -1.07
    AndEndTag
    -1.05
    ConstraintMaker
    -1.01
    __':
    
    -0.98
     $_"
    -0.97
     Efq
    -0.96
    
    -0.96
     فريبيس
    -0.94
     AssemblyCulture
    -0.93
    POSITIVE LOGITS
     is
    0.59
     and
    0.52
    tis
    0.43
    us
    0.42
    ไ
    0.41
     needs
    0.41
     known
    0.41
     علا
    0.40
     &
    0.38
     works
    0.37
    Activations Density 3.547%

    No Known Activations