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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16260
    Prev
    Next
    INDEX
    Explanations

    various bits of Java and C code.

    oai_token-act-pair · gemini-2.0-flash

    code characters

    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
     Efq
    -2.14
     myſelf
    -2.11
     Monfieur
    -1.96
     Theſe
    -1.89
     Majefty
    -1.88
     doubtnut
    -1.85
     itſelf
    -1.84
     purpoſe
    -1.84
     Jefus
    -1.80
     Houſe
    -1.80
    POSITIVE LOGITS
     -
    0.96
     
    0.91
     –
    0.91
    ’
    0.90
     (
    0.90
     —
    0.88
    co
    0.88
    ,
    0.88
     =
    0.88
    </i>
    0.87
    Activations Density 5.339%

    No Known Activations