© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2450
    Prev
    Next
    INDEX
    Explanations

    text with dates, codes, and other identifiers, especially from more technical documents

    oai_token-act-pair · gemini-2.0-flash

    programming syntax or code elements

    np_token-act-pair-logits · gpt-4o-mini

    Code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     recent
    -0.29
     late
    -0.27
     (
    -0.27
     and
    -0.25
     success
    -0.25
    ↵
    -0.25
     punishment
    -0.24
     uniform
    -0.24
     duty
    -0.23
     /^\
    -0.23
    POSITIVE LOGITS
    <bos>
    0.80
     AssemblyTitle
    0.59
     Normdatei
    0.59
    writeFieldEnd
    0.58
    ########.
    0.56
    featureID
    0.55
     utafitiHapana
    0.55
    }*/
    0.55
    )*/
    0.55
    });*/
    0.54
    Activations Density 3.873%

    No Known Activations