© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14102
    Prev
    Next
    INDEX
    Explanations

    clauses describing beliefs and values

    oai_token-act-pair · gemini-2.0-flash

    moral judgements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     alimentaires
    -0.46
     aéreas
    -0.46
     écoles
    -0.42
    webElement
    -0.42
     personalità
    -0.42
     graphiques
    -0.41
    endpush
    -0.40
    RunWith
    -0.40
     numberWith
    -0.40
     présidentielle
    -0.39
    POSITIVE LOGITS
    ]--;
    0.85
    ########.
    0.83
    ]")]
    0.66
    ].)
    0.66
    SerializedSize
    0.65
    nocześnie
    0.63
    })$}
    0.60
     INSEE
    0.59
    ///</
    0.59
     castor
    0.59
    Activations Density 8.457%

    No Known Activations