© 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. 10589
    Prev
    Next
    INDEX
    Explanations

    conditional statements including the personal pronouns 'she', 'he', and 'they'.

    oai_token-act-pair · gemini-2.0-flash

    step 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_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
     NSCoder
    -0.98
    +#+#
    -0.87
    CodedInputStream
    -0.70
     Pública
    -0.70
    BufferException
    -0.68
    ruptedException
    -0.65
     Inde
    -0.63
    esModule
    -0.62
     المعيارى
    -0.62
     Fid
    -0.61
    POSITIVE LOGITS
     set
    1.38
     step
    1.23
     Set
    1.23
     stepped
    1.22
    step
    1.15
    Set
    1.14
     setting
    1.13
     foot
    1.13
    Step
    1.13
     steps
    1.09
    Activations Density 0.913%

    No Known Activations