© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36755
    Prev
    Next
    INDEX
    Explanations

    pH and ionization state

    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
    hide
    0.38
     hide
    0.38
     hides
    0.38
    ereza
    0.37
     ecol
    0.36
    篑
    0.36
    둑
    0.35
    覀
    0.35
     کرتی
    0.35
     hid
    0.35
    POSITIVE LOGITS
    Nuevo
    0.39
     ghost
    0.38
    Stable
    0.37
    bcrypt
    0.37
    Un
    0.37
    Neu
    0.36
     Coupling
    0.36
     nationalities
    0.35
     alrededores
    0.35
    ghost
    0.35
    Activations Density 0.026%

    No Known Activations