© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153280
    Prev
    Next
    INDEX
    Explanations

    what something does

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    0.46
     Kapp
    0.45
     Am
    0.45
     Petro
    0.44
     Joz
    0.42
     Loves
    0.42
     *
    0.41
     Was
    0.41
     Alic
    0.41
     Takes
    0.41
    POSITIVE LOGITS
    </strong>
    0.69
    </h4>
    0.54
    </u>
    0.54
    divide
    0.51
    </s>
    0.49
    </em>
    0.47
    find
    0.46
    bring
    0.46
    write
    0.45
    </sub>
    0.44
    Activations Density 0.008%

    No Known Activations