© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12664
    Prev
    Next
    INDEX
    Explanations

    the word "finish" or "finished" related to a competition, product or other endeavor

    oai_token-act-pair · gemini-2.0-flash

    finish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     finish
    -2.48
     Finish
    -2.20
    finish
    -2.16
     finishes
    -2.00
    Finish
    -1.99
     finishing
    -1.98
     FINISH
    -1.98
     Finishing
    -1.85
    finishing
    -1.82
    Finishing
    -1.76
    POSITIVE LOGITS
     itſelf
    0.73
    ")));
    0.67
     betweenstory
    0.65
     Theſe
    0.60
    uxxxx
    0.60
     Eſ
    0.60
     myſelf
    0.59
     tartalomajánló
    0.59
     himſelf
    0.57
    ValueGeneration
    0.57
    Activations Density 0.425%

    No Known Activations