© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129352
    Prev
    Next
    INDEX
    Explanations

    developers

    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_6_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
     is
    1.29
    ↵↵
    1.13
    z
    1.11
    p
    1.08
     "
    1.06
     was
    1.04
     de
    1.02
    \
    1.01
     you
    1.00
    t
    0.99
    POSITIVE LOGITS
    其他
    0.91
     ఇచ్చ
    0.87
     தெரிவித்த
    0.86
     effectuées
    0.85
    發生
    0.84
    ότητας
    0.84
     നിന്നും
    0.83
     অ্যাস
    0.83
     поги
    0.82
     службы
    0.79
    Activations Density 0.008%

    No Known Activations