© 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
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 10781
    Prev
    Next
    INDEX
    Explanations

    the word "of" preceded or followed by the words "much" or "the".

    oai_token-act-pair · gemini-2.0-flash

    as or of

    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
    CPtr
    -0.61
     Roskov
    -0.60
    troppo
    -0.56
     mínima
    -0.55
     refroid
    -0.54
     compéti
    -0.54
     voeten
    -0.53
    readystatechange
    -0.52
    mistry
    -0.52
     malheure
    -0.52
    POSITIVE LOGITS
    <bos>
    1.88
     })}
    0.69
    }).
    0.64
    }}
    0.62
    }());
    0.62
    ti
    0.60
    ()).
    0.58
    oy
    0.58
    ).}
    0.57
    ))=\
    0.57
    Activations Density 0.440%

    No Known Activations