© 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. 2178
    Prev
    Next
    INDEX
    Explanations

    text from scientific papers about dietary effects

    oai_token-act-pair · gemini-2.0-flash

    gut flora

    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
    Referencie
    -0.52
    </thead>
    -0.52
    Personendaten
    -0.51
    )։
    -0.49
     boli
    -0.47
     thiệu
    -0.46
     Вікі
    -0.46
     dAtA
    -0.45
     len
    -0.44
    Lähteet
    -0.44
    POSITIVE LOGITS
    DebuggerNonUser
    0.77
    +:+
    0.63
    󠁢
    0.59
    tvguidetime
    0.57
    ValueOf
    0.56
     виправивши
    0.56
    ierenden
    0.50
     Unidas
    0.50
     judiciaire
    0.50
    ilado
    0.49
    Activations Density 1.398%

    No Known Activations