© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13900
    Prev
    Next
    INDEX
    Explanations

    text relating to shrimp farming and probiotics in the Pacific.

    oai_token-act-pair · gemini-2.0-flash

    shrimp biology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     صوتيه
    -0.52
     كومونز
    -0.47
    <bos>
    -0.47
     numberWith
    -0.45
    moveToNext
    -0.45
    ssil
    -0.44
    CPtr
    -0.44
    __*/
    -0.42
     virtuel
    -0.42
     Gier
    -0.41
    POSITIVE LOGITS
    UnknownFieldSet
    0.69
    post
    0.61
     marinho
    0.61
     post
    0.60
     Stratton
    0.59
    postIndex
    0.58
    cesis
    0.58
     propOrder
    0.57
    Jîn
    0.57
    Activités
    0.57
    Activations Density 2.805%

    No Known Activations