© 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. 15725
    Prev
    Next
    INDEX
    Explanations

    language about truth, authority, and belief

    oai_token-act-pair · gemini-2.0-flash

    writing

    np_max-act-logits · 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
     vPvB
    -0.37
     aceptas
    -0.36
    gató
    -0.33
     prá
    -0.33
     ře
    -0.33
    стов
    -0.33
    or
    -0.33
    <bos>
    -0.32
     piac
    -0.32
     JUGA
    -0.32
    POSITIVE LOGITS
     poem
    0.88
     assumption
    0.84
     lèvres
    0.83
    poem
    0.83
     recipe
    0.82
    parsedMessage
    0.82
     epithet
    0.82
     bouquet
    0.81
     gesture
    0.81
     allegation
    0.79
    Activations Density 45.789%

    No Known Activations