© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 51668
    Prev
    Next
    INDEX
    Explanations

    envisioning oneself or futures

    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
    abez
    0.39
    與
    0.38
    akte
    0.38
     unfairly
    0.37
    armes
    0.37
    rade
    0.37
     Alarm
    0.37
    上
    0.37
    阵
    0.37
    ழி
    0.36
    POSITIVE LOGITS
     envisioned
    0.67
     envisaged
    0.61
     envision
    0.59
     envisions
    0.55
     imagined
    0.54
     envisage
    0.51
     foreseen
    0.47
     futuro
    0.46
     مستقبل
    0.45
     Imag
    0.44
    Activations Density 0.025%

    No Known Activations