© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4444
    Prev
    Next
    INDEX
    Explanations

    biological terms related to cell functions, processes, and structures.

    oai_token-act-pair · gemini-2.0-flash

    cell division, repair

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     blessés
    -0.56
    amera
    -0.53
     doigts
    -0.52
    wezen
    -0.50
     münd
    -0.49
    треть
    -0.49
    Portail
    -0.48
     police
    -0.47
    Ligações
    -0.47
    Profes
    -0.46
    POSITIVE LOGITS
    tableFuture
    0.68
    AndEndTag
    0.66
    TargetException
    0.63
    JoinTable
    0.63
     biologique
    0.62
     bioavailability
    0.61
    EndContext
    0.60
    Brainz
    0.59
    tagHelper
    0.59
    BagConstraints
    0.58
    Activations Density 2.532%

    No Known Activations