© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200380
    Prev
    Next
    INDEX
    Explanations

    forms of energy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     water
    0.49
    水
    0.47
     nước
    0.46
     Water
    0.45
    water
    0.44
     पानी
    0.43
     پانی
    0.43
     Chiron
    0.42
    Water
    0.41
     WATER
    0.41
    POSITIVE LOGITS
    Fade
    0.38
    нец
    0.38
    ieth
    0.38
    让他们
    0.37
    wij
    0.37
    潛
    0.37
    cfp
    0.37
     চল
    0.35
     केमिक
    0.35
    Plug
    0.35
    Activations Density 0.004%

    No Known Activations