© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9995
    Prev
    Next
    INDEX
    Explanations

    references to academic publications, especially the years and some keywords

    oai_token-act-pair · gemini-2.0-flash

    closing parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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>
    -0.69
    XDECREF
    -0.46
    }),
    -0.44
    [];
    -0.43
    ’
    -0.43
     gabbana
    -0.42
     "");
    -0.42
    ]);
    -0.42
    ]),
    -0.40
    /");
    -0.40
    POSITIVE LOGITS
    bootstrapcdn
    0.93
     تضيفلها
    0.88
     Theſe
    0.73
     themſelves
    0.71
     myſelf
    0.70
    ंदीखरीदारी
    0.69
     pleaſure
    0.67
     виправивши
    0.67
     faſt
    0.66
     ſta
    0.66
    Activations Density 0.740%

    No Known Activations