© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12454
    Prev
    Next
    INDEX
    Explanations

    the word "end" and words that proceed and follow it

    oai_token-act-pair · gemini-2.0-flash

    end

    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
     End
    -2.30
     END
    -2.08
    End
    -2.06
     Ends
    -2.02
     end
    -1.95
     ends
    -1.88
     Ending
    -1.88
     ending
    -1.84
    END
    -1.79
    end
    -1.70
    POSITIVE LOGITS
    eseorang
    0.43
     quantità
    0.43
    exprimer
    0.43
    engager
    0.41
     birra
    0.40
    entraînement
    0.38
     an
    0.37
     singur
    0.37
     helpen
    0.37
     quantités
    0.37
    Activations Density 1.775%

    No Known Activations