© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203221
    Prev
    Next
    INDEX
    Explanations

    want to / need to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     %),
    0.66
     %).
    0.61
     അംഗ
    0.59
    aphylococcus
    0.56
    ！)
    0.55
     %)
    0.54
    )',
    0.54
    %);
    0.54
    apixel
    0.54
     \%)$.
    0.54
    POSITIVE LOGITS
    Need
    0.84
     need
    0.82
    Needs
    0.76
    need
    0.75
     Need
    0.74
     Needs
    0.73
    a
    0.73
     Needed
    0.72
     NEED
    0.71
    an
    0.71
    Activations Density 0.000%

    No Known Activations