© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7515
    Prev
    Next
    INDEX
    Explanations

    clauses separated by dashes

    oai_token-act-pair · gemini-2.0-flash

    dashes and parentheses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    –
    -0.45
    d
    -0.44
    o
    -0.42
    com
    -0.41
    di
    -0.41
    dy
    -0.41
    -
    -0.40
    st
    -0.40
    mit
    -0.40
    av
    -0.39
    POSITIVE LOGITS
     "..\..\
    0.58
    ToAction
    0.56
    AndEndTag
    0.55
     vectorielle
    0.54
    bootstrapcdn
    0.52
    IntoConstraints
    0.52
     vettor
    0.52
     Bucure
    0.52
    Viitteet
    0.52
     OnInit
    0.51
    Activations Density 7.967%

    No Known Activations