© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8904
    Prev
    Next
    INDEX
    Explanations

    electron states and levels

    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_40_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
     Managed
    0.30
     managed
    0.29
     रॉ
    0.28
     ann
    0.28
    絘
    0.27
     styled
    0.26
     servent
    0.25
    Managed
    0.25
     消
    0.25
    ParaName
    0.24
    POSITIVE LOGITS
    states
    0.61
     states
    0.59
     levels
    0.49
     estados
    0.49
    state
    0.48
    levels
    0.48
     STATES
    0.47
     LEVELS
    0.47
    States
    0.46
     state
    0.46
    Activations Density 0.061%

    No Known Activations