© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7934
    Prev
    Next
    INDEX
    Explanations

    snippets of C++ code

    oai_token-act-pair · gemini-2.0-flash

    code brackets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    -1.12
    ſelf
    -1.03
     myſelf
    -1.00
     Monfieur
    -0.99
    ſelves
    -0.92
     ―――――
    -0.91
     iſt
    -0.87
     Jefus
    -0.85
     Efq
    -0.84
    NUMX
    -0.84
    POSITIVE LOGITS
    ↵
    0.53
     F
    0.50
     c
    0.50
     B
    0.45
     f
    0.44
     C
    0.44
     then
    0.44
    iri
    0.43
     I
    0.43
    <eos>
    0.42
    Activations Density 3.308%

    No Known Activations