© 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-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 150863
    Prev
    Next
    INDEX
    Explanations

    refuse harmful prompts

    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
    <b>
    0.44
    ↵
    0.41
    Jetzt
    0.41
    ி
    0.41
     ،
    0.39
    <strong>
    0.38
    **,
    0.38
    .,
    0.37
    **
    0.37
    以下の
    0.37
    POSITIVE LOGITS
     we
    0.72
     you
    0.62
     мы
    0.51
     We
    0.51
     All
    0.51
     우리는
    0.48
     she
    0.46
     você
    0.45
     am
    0.45
     我們
    0.45
    Activations Density 0.008%

    No Known Activations