© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13003
    Prev
    Next
    INDEX
    Explanations

    references to software updates and news publications

    oai_token-act-pair · gemini-2.0-flash

    say "</b>"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    </i>
    -3.13
    </b>
    -2.34
    <b>
    -2.31
    <i>
    -2.09
    </em>
    -1.28
    </s>
    -1.20
    </h3>
    -1.18
    </td>
    -1.07
    </u>
    -1.03
    </h2>
    -1.00
    POSITIVE LOGITS
     fi
    1.20
     fl
    1.14
    fl
    1.13
     
    1.08
     first
    1.05
    fi
    1.02
    ."""
    1.02
     
    0.94
     """
    0.88
     """
    0.87
    Activations Density 0.213%

    No Known Activations