© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3731
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to research or figuring things out.

    oai_token-act-pair · gemini-2.0-flash

    finding a solution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    }$}
    -0.53
     """
    -0.51
     alternatives
    -0.47
     fixed
    -0.47
    وفير
    -0.46
    ']));
    -0.44
    kiel
    -0.43
     screen
    -0.42
     fix
    -0.41
    )}
    -0.41
    POSITIVE LOGITS
     Theſe
    0.78
     pleaſure
    0.76
     Houſe
    0.75
     houſe
    0.73
     Monfieur
    0.71
     myſelf
    0.69
     purpoſe
    0.69
     deſt
    0.67
     Reſ
    0.66
    ſelf
    0.66
    Activations Density 11.526%

    No Known Activations