© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14756
    Prev
    Next
    INDEX
    Explanations

    the prefixes "Tha" or "Na" followed by some other sound

    oai_token-act-pair · gemini-2.0-flash

    'Tha' related terms

    np_token-act-pair-logits · gpt-4o-mini

    Scientific text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     polvo
    -0.45
     levure
    -0.41
     rå
    -0.39
    twimg
    -0.39
    kloped
    -0.38
    imoto
    -0.38
    先代
    -0.37
     elő
    -0.36
     cel
    -0.36
    elden
    -0.36
    POSITIVE LOGITS
    RetentionPolicy
    1.00
    IntoConstraints
    0.72
    rrggbb
    0.72
    原始内容存档于
    0.68
    DebuggerNonUser
    0.66
    InstrumentedTest
    0.62
    MessageState
    0.60
    #
    0.60
     ProtoMessage
    0.59
    Specificity
    0.59
    Activations Density 0.631%

    No Known Activations