© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32991
    Prev
    Next
    INDEX
    Explanations

    states, relationships

    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_31_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
     meaning
    0.39
    ƒ
    0.38
     administrators
    0.38
     Eld
    0.36
    meaning
    0.36
     নায়
    0.36
     Miller
    0.35
     বাঙ্গাল
    0.35
    ILD
    0.35
    alla
    0.34
    POSITIVE LOGITS
    flip
    0.38
    revoke
    0.37
    Flip
    0.37
     冖
    0.36
     chấm
    0.36
    icone
    0.35
     फ्लिप
    0.35
     Tilt
    0.35
    شارات
    0.35
     ".",
    0.34
    Activations Density 0.002%

    No Known Activations