© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5576
    Prev
    Next
    INDEX
    Explanations

    floating point numbers in scientific notation consisting of two numbers separated by "E+"

    oai_token-act-pair · gemini-2.0-flash

    Numbers, decimals

    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
     itſelf
    -0.96
    ſelf
    -0.83
    ſelves
    -0.82
     Shakspeare
    -0.82
     myſelf
    -0.79
     Efq
    -0.77
     raiſ
    -0.75
     Monfieur
    -0.75
     Jefus
    -0.75
     ſeveral
    -0.73
    POSITIVE LOGITS
     $
    0.82
     ($
    0.77
    $
    0.76
    -$
    0.69
    =$
    0.68
     $\
    0.66
    )$
    0.65
     }$
    0.65
    }$
    0.65
    ,$
    0.65
    Activations Density 22.911%

    No Known Activations