© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12960
    Prev
    Next
    INDEX
    Explanations

    words used in a conversational tone, which can be used to indicate different types of speech or writing

    oai_token-act-pair · gemini-2.0-flash

    uncertainty or opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    ."],
    -0.66
    \}^{
    -0.53
    ]--;
    -0.53
    "},
    -0.50
    ]>=
    -0.50
    orini
    -0.50
    ]=-
    -0.50
    }');
    -0.50
    acchi
    -0.50
    ."]
    -0.49
    POSITIVE LOGITS
    enumii
    0.85
    UnusedPrivate
    0.84
     مشين
    0.78
     pinulongan
    0.74
    posedge
    0.74
    :✨
    0.73
    InstrumentedTest
    0.73
    جوايز
    0.66
     Abp
    0.65
     nahilalakip
    0.65
    Activations Density 49.784%

    No Known Activations