© 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. 15767
    Prev
    Next
    INDEX
    Explanations

    bracketed expressions containing "r" and "l".

    oai_token-act-pair · gemini-2.0-flash

    r

    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
    <bos>
    -0.89
    твра
    -0.68
     picioare
    -0.66
    Попис
    -0.66
     onely
    -0.65
     ägg
    -0.64
     gouttes
    -0.64
     női
    -0.63
     fleurs
    -0.62
     câte
    -0.62
    POSITIVE LOGITS
    })`
    0.62
    WritableDatabase
    0.60
     deng
    0.59
    }`;
    0.57
     متعلقه
    0.56
    ComponentModel
    0.54
    ništvo
    0.54
     istr
    0.52
    Einzelnachweise
    0.50
     BoxDecoration
    0.50
    Activations Density 0.644%

    No Known Activations