© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13218
    Prev
    Next
    INDEX
    Explanations

    words and short phrases that frequently occur in political debate and history contexts

    oai_token-act-pair · gemini-2.0-flash

    conflict/disputes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    __":
    -0.73
    хьтан
    -0.60
    Personensuche
    -0.57
    })}$
    -0.57
     Obrador
    -0.57
     ddelweddau
    -0.54
    ErrUnexpectedEOF
    -0.53
    }}}$
    -0.53
     Normdatei
    -0.52
    formaz
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.57
    makeConstraints
    0.46
     alignItems
    0.44
    nambuco
    0.43
    acate
    0.42
    AlterField
    0.42
     gesteld
    0.41
    usel
    0.41
    <_>
    0.41
    териалы
    0.41
    Activations Density 2.880%

    No Known Activations