© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14061
    Prev
    Next
    INDEX
    Explanations

    a mix of publication metadata, including journal names, numbers, months, and author name parts

    oai_token-act-pair · gemini-2.0-flash

    |

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    webElementXpaths
    -0.60
     beginnetje
    -0.56
     tarko
    -0.54
    marshaller
    -0.52
    بوابة
    -0.50
     répondit
    -0.50
    thâu
    -0.50
     Majesté
    -0.49
     للاسماء
    -0.49
    لاثة
    -0.47
    POSITIVE LOGITS
    itinéraire
    0.53
    uled
    0.52
    thick
    0.50
    pushFollow
    0.50
    Affirmed
    0.50
    ldorf
    0.50
    <?>>
    0.49
     ब्रेकडाउन
    0.49
     thumb
    0.47
     endregion
    0.47
    Activations Density 0.636%

    No Known Activations