© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3095
    Prev
    Next
    INDEX
    Explanations

    instances of holding, permitting, or revealing

    oai_token-act-pair · gemini-2.0-flash

    hold

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     hold
    -2.81
    hold
    -2.53
     holds
    -2.50
     holding
    -2.48
     Hold
    -2.47
    Hold
    -2.45
     held
    -2.34
     HOLD
    -2.34
    HOLD
    -2.28
     Holds
    -2.19
    POSITIVE LOGITS
    eseorang
    0.52
    }))
    0.49
    ])));
    0.49
     serializers
    0.49
    )?;
    0.47
    ioneers
    0.47
     sympathies
    0.45
    setVerticalGroup
    0.44
     seam
    0.44
     Appe
    0.44
    Activations Density 6.949%

    No Known Activations