© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7081
    Prev
    Next
    INDEX
    Explanations

    seemingly random and diverse topics, but with a focus on sentences punctuated in a particular way

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code-related phrases

    np_token-act-pair-logits · gpt-4o-mini

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ]$}
    -0.49
    ).]
    -0.47
    }*/
    -0.42
    )$}
    -0.41
    {}/
    -0.41
    oult
    -0.40
    ://$
    -0.36
    //}
    -0.36
    .},
    -0.35
    exion
    -0.35
    POSITIVE LOGITS
    httphttps
    0.77
    GraphicsUnit
    0.73
    ContentAlignment
    0.71
    PullParser
    0.71
    SetBool
    0.71
    StoryboardSegue
    0.69
     AssemblyCulture
    0.67
    parsedMessage
    0.67
    ValueStyle
    0.67
    তথ্যসূত্র
    0.66
    Activations Density 4.251%

    No Known Activations