© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 10436
    Prev
    Next
    INDEX
    Explanations

    the word "ending" or words ending in "ing"

    oai_token-act-pair · gemini-2.0-flash

    ending

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.13
    end
    -0.85
    <eos>
    -0.79
     the
    -0.77
      
    -0.77
     a
    -0.76
    <b>
    -0.75
    </b>
    -0.74
    END
    -0.72
     $
    -0.71
    POSITIVE LOGITS
     auffi
    1.41
     Efq
    1.30
    ſelves
    1.30
     itſelf
    1.28
     ―――――
    1.27
    ſelf
    1.27
     myſelf
    1.27
     Monfieur
    1.25
     ſind
    1.20
     doubtnut
    1.18
    Activations Density 1.316%

    No Known Activations