© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 15164
    Prev
    Next
    INDEX
    Explanations

    the variable 'i' used in a C or C++ loop

    oai_token-act-pair · gemini-2.0-flash

    code loops

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    Geplaatst
    -0.65
     onAnimation
    -0.53
     standout
    -0.51
    asher
    -0.50
    saraba
    -0.49
    AndEndTag
    -0.49
    InSection
    -0.48
     favorite
    -0.48
     converting
    -0.47
    TypedDataSet
    -0.46
    POSITIVE LOGITS
     Efq
    0.93
     Majefty
    0.88
     Monfieur
    0.85
     purpoſe
    0.75
     itſelf
    0.74
     Jefus
    0.72
     houſe
    0.71
     Houſe
    0.70
     fubject
    0.70
     poffible
    0.69
    Activations Density 0.202%

    No Known Activations