© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14743
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to dining and trails

    oai_token-act-pair · gemini-2.0-flash

    positive reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    parsedMessage
    -0.56
    RegistryLite
    -0.53
    reditation
    -0.49
    OrBuilder
    -0.49
    uito
    -0.48
    ractable
    -0.48
     toner
    -0.47
    plier
    -0.47
    뀜
    -0.46
    Демографія
    -0.45
    POSITIVE LOGITS
    DIPSETTING
    0.60
    OOTDTY
    0.56
     Normdatei
    0.52
     ModelRenderer
    0.52
    apunov
    0.52
     AppModule
    0.50
     attiva
    0.50
    """
    0.50
    ❋
    0.50
     onCreateView
    0.49
    Activations Density 15.536%

    No Known Activations