© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1984
    Prev
    Next
    INDEX
    Explanations

    words starting with "ter" or ending with "eded," "eaker," "eing," or "eazy."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ometers
    -0.45
    on
    -0.43
    SequentialGroup
    -0.42
    جان
    -0.41
    indépendance
    -0.41
    ука
    -0.38
    okka
    -0.38
    naphthal
    -0.36
     y
    -0.36
     de
    -0.36
    POSITIVE LOGITS
     tartalomajánló
    0.90
    +#+#
    0.90
     autorytatywna
    0.87
    aarrggbb
    0.82
    featureID
    0.73
    uxxxx
    0.72
    InitVars
    0.70
    twimg
    0.68
    ########.
    0.66
    MessageOf
    0.65
    Activations Density 1.355%

    No Known Activations