© 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. 5658
    Prev
    Next
    INDEX
    Explanations

    nouns followed by commas and numbers

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     includes
    -2.36
     include
    -2.34
     Includes
    -2.09
     Including
    -2.00
    includes
    -1.99
     Include
    -1.99
    Includes
    -1.98
    Including
    -1.96
     INCLUDE
    -1.86
    Include
    -1.85
    POSITIVE LOGITS
     فريبيس
    0.59
    ArgsConstructor
    0.58
    AxisAlignment
    0.57
    Viitteet
    0.55
    SequentialGroup
    0.55
     AttributeSet
    0.55
     Permalink
    0.52
     Normdatei
    0.51
    WebVitals
    0.51
    shadowOffset
    0.49
    Activations Density 3.722%

    No Known Activations