© 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. 9199
    Prev
    Next
    INDEX
    Explanations

    abstract nouns that end in "-tion", and possibly also words related to politics and negative opinions

    oai_token-act-pair · gemini-2.0-flash

    Adding or the presence of

    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
    ConstraintMaker
    -0.96
    AccessorTable
    -0.90
    __':
    -0.85
    __':
    -0.83
    UnsafeEnabled
    -0.81
    ChildScrollView
    -0.81
    Lähteet
    -0.79
    __":
    -0.79
    StoryboardSegue
    -0.76
    PRNewswire
    -0.73
    POSITIVE LOGITS
     equal
    0.41
     izvē
    0.40
    AnchorTagHelper
    0.39
    InSection
    0.38
    tology
    0.37
    amatkan
    0.37
    appi
    0.36
    equal
    0.36
    she
    0.35
    gento
    0.35
    Activations Density 0.434%

    No Known Activations