© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54313
    Prev
    Next
    INDEX
    Explanations

    historical periods and upheaval

    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
     waterproof
    0.38
    ಾರಿ
    0.38
     Jé
    0.36
    )^{*
    0.35
     श्र
    0.35
     ambienti
    0.35
     afore
    0.35
     cursos
    0.34
     volant
    0.34
     renewable
    0.34
    POSITIVE LOGITS
    เดิน
    0.38
    ヨーク
    0.38
    军
    0.38
    欢乐
    0.38
    短暂
    0.38
    nmea
    0.37
     Navigation
    0.37
    rollen
    0.36
     decoy
    0.36
    stanford
    0.36
    Activations Density 0.010%

    No Known Activations