© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9197
    Prev
    Next
    INDEX
    Explanations

    English prepositions and action verbs

    oai_token-act-pair · gemini-2.0-flash

    phrasal verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     FetchType
    -0.59
     RSSSF
    -0.56
    ✨:
    -0.55
     utafitiHapana
    -0.54
     cherchés
    -0.54
     homology
    -0.52
    الدراسه
    -0.50
     Vikipedi
    -0.49
     surla
    -0.49
    RenderAtEndOf
    -0.48
    POSITIVE LOGITS
     EdgeInsets
    0.59
     ''
    0.57
     للاسماء
    0.55
    }}
    0.54
     the
    0.53
    })*/
    0.53
    }{$
    0.51
    ficial
    0.50
     ré
    0.49
    iori
    0.49
    Activations Density 3.698%

    No Known Activations