© 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. 4862
    Prev
    Next
    INDEX
    Explanations

    pronouns joined by conjunctions

    oai_token-act-pair · gemini-2.0-flash

    realizing, knowing

    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
     right
    -0.64
    right
    -0.55
    MigrationBuilder
    -0.52
    zzleHttp
    -0.50
    #+#
    -0.49
     correct
    -0.49
     onCreateView
    -0.48
    Rtl
    -0.47
    recht
    -0.47
     RIGHT
    -0.47
    POSITIVE LOGITS
     realised
    1.00
     realises
    0.99
     realize
    0.99
     realise
    0.99
     realized
    0.97
     realizes
    0.96
     knew
    0.93
    Know
    0.88
     know
    0.85
     knows
    0.82
    Activations Density 2.291%

    No Known Activations