© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5330
    Prev
    Next
    INDEX
    Explanations

    a general pattern of conjunctions and personal pronouns, often in the context of creating something

    oai_token-act-pair · gemini-2.0-flash

    saying "done"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    bcryptjs
    -0.56
    GEBURTSDATUM
    -0.53
    PhysRevLett
    -0.48
    noinspection
    -0.47
    ocities
    -0.43
     Lordships
    -0.43
     Zwer
    -0.43
    abro
    -0.42
     HasFactory
    -0.42
    avelmente
    -0.42
    POSITIVE LOGITS
     Done
    1.23
    done
    1.18
    Done
    1.17
     done
    1.16
     DONE
    1.01
    DONE
    0.91
     finished
    0.88
     Finished
    0.82
     klaar
    0.79
     Completed
    0.79
    Activations Density 2.101%

    No Known Activations