© 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. 14786
    Prev
    Next
    INDEX
    Explanations

    the suffix "th" attached to a number

    oai_token-act-pair · gemini-2.0-flash

    th

    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
    <bos>
    -0.49
    r
    -0.46
     இரு
    -0.45
     it
    -0.42
    帖最后由
    -0.42
    which
    -0.41
     zurückge
    -0.41
    and
    -0.41
    we
    -0.40
     and
    -0.40
    POSITIVE LOGITS
     المعيارى
    1.05
     fourth
    0.98
     second
    0.96
     AssemblyCulture
    0.95
     third
    0.93
     fifth
    0.92
    DoubleQuotes
    0.92
     Second
    0.90
     Fourth
    0.90
    second
    0.88
    Activations Density 0.781%

    No Known Activations